由Difan Deng和Marius Lindauer维护。
以下列表包含与神经架构搜索相关的论文。它绝非完整。如果您发现列表中缺少某篇论文，请告知我们。
请注意，尽管NAS方法稳步改进，但该领域的实证评估质量仍落后于机器学习、人工智能和优化等其他领域。因此，我们希望分享一些NAS方法实证评估的最佳实践，我们相信这将促进该领域持续和可衡量的进展。如果您想先睹为快，请阅读我们的博客文章或直接查看我们的清单。
Transformers在不同领域越来越受欢迎。有关专注于基于Transformer的神经架构搜索的论文的综合列表，awesome-transformer-search库提供了您所需的一切。
5555
4488.
朱慧娟；夏梦真；王良民；徐志成；盛维克多S.
一种用于Android恶意软件检测的新型知识搜索结构 期刊文章
收录于：IEEE Transactions on Services Computing，第01期，第1-14页，5555年，ISSN：1939-1374。
@article{10750332,
title = { A Novel Knowledge Search Structure for Android Malware Detection },
author = {Huijuan Zhu and Mengzhen Xia and Liangmin Wang and Zhicheng Xu and Victor S. Sheng},
url = {https://doi.ieeecomputersociety.org/10.1109/TSC.2024.3496333},
doi = {10.1109/TSC.2024.3496333},
issn = {1939-1374},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Services Computing},
number = {01},
pages = {1-14},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {While the Android platform is gaining explosive popularity, the number of malicious software (malware) is also increasing sharply. Thus, numerous malware detection schemes based on deep learning have been proposed. However, they are usually suffering from the cumbersome models with complex architectures and tremendous parameters. They usually require heavy computation power support, which seriously limit their deployment on actual application environments with limited resources (e.g., mobile edge devices). To surmount this challenge, we propose a novel Knowledge Distillation (KD) structure—Knowledge Search (KS). KS exploits Neural Architecture Search (NAS) to adaptively bridge the capability gap between teacher and student networks in KD by introducing a parallelized student-wise search approach. In addition, we carefully analyze the characteristics of malware and locate three cost-effective types of features closely related to malicious attacks, namely, Application Programming Interfaces (APIs), permissions and vulnerable components, to characterize Android Applications (Apps). Therefore, based on typical samples collected in recent years, we refine features while exploiting the natural relationship between them, and construct corresponding datasets. Massive experiments are conducted to investigate the effectiveness and sustainability of KS on these datasets. Our experimental results show that the proposed method yields an accuracy of 97.89% to detect Android malware, which performs better than state-of-the-art solutions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
随着Android平台的爆炸式普及，恶意软件（malware）的数量也急剧增加。因此，基于深度学习的恶意软件检测方案层出不穷。然而，这些方案通常受限于模型臃肿、架构复杂和参数量巨大。它们通常需要强大的计算能力支持，这严重限制了它们在资源有限的实际应用环境（例如移动边缘设备）中的部署。为了克服这一挑战，我们提出了一种新颖的知识蒸馏（KD）结构——知识搜索（KS）。KS利用神经架构搜索（NAS）通过引入并行化的学生端搜索方法，自适应地弥合KD中教师网络和学生网络之间的能力差距。此外，我们仔细分析了恶意软件的特征，并定位了三种与恶意攻击密切相关的经济高效的特征类型，即应用程序编程接口（API）、权限和易受攻击的组件，以表征Android应用程序（Apps）。因此，我们基于近年来收集的典型样本，在利用它们之间固有关系的同时，提炼出特征，并构建了相应的数据集。我们进行了大量实验，以研究KS在这些数据集上的有效性和可持续性。我们的实验结果表明，所提出的方法在检测Android恶意软件方面达到了97.89%的准确率，优于最先进的解决方案。
4487.
张菲菲；李茂；葛继东；唐凤辉；张晟；吴杰；罗斌
边缘计算中具有增强鲁棒性的隐私保护联邦神经架构搜索 期刊文章
收录于：IEEE Transactions on Mobile Computing，第01期，第1-18页，5555年，ISSN：1558-0660。
@article{10742476,
title = { Privacy-Preserving Federated Neural Architecture Search With Enhanced Robustness for Edge Computing },
author = {Feifei Zhang and Mao Li and Jidong Ge and Fenghui Tang and Sheng Zhang and Jie Wu and Bin Luo},
url = {https://doi.ieeecomputersociety.org/10.1109/TMC.2024.3490835},
doi = {10.1109/TMC.2024.3490835},
issn = {1558-0660},
year = {5555},
date = {5555-11-01},
urldate = {5555-11-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-18},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {With the development of large-scale artificial intelligence services, edge devices are becoming essential providers of data and computing power. However, these edge devices are not immune to malicious attacks. Federated learning (FL), while protecting privacy of decentralized data through secure aggregation, struggles to trace adversaries and lacks optimization for heterogeneity. We discover that FL augmented with Differentiable Architecture Search (DARTS) can improve resilience against backdoor attacks while compatible with secure aggregation. Based on this, we propose a federated neural architecture search (NAS) framwork named SLNAS. The architecture of SLNAS is built on three pivotal components: a server-side search space generation method that employs an evolutionary algorithm with dual encodings, a federated NAS process based on DARTS, and client-side architecture tuning that utilizes Gumbel softmax combined with knowledge distillation. To validate robustness, we adapt a framework that includes backdoor attacks based on trigger optimization, data poisoning, and model poisoning, targeting both model weights and architecture parameters. Extensive experiments demonstrate that SLNAS not only effectively counters advanced backdoor attacks but also handles heterogeneity, outperforming defense baselines across a wide range of backdoor attack scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
随着大规模人工智能服务的发展，边缘设备正成为数据和计算能力的重要提供者。然而，这些边缘设备并非对恶意攻击免疫。联邦学习（FL）虽然通过安全聚合保护了去中心化数据的隐私，但在追踪攻击者方面仍面临挑战，并且缺乏对异构性的优化。我们发现，通过可微分架构搜索（DARTS）增强的FL可以提高对后门攻击的弹性，同时与安全聚合兼容。在此基础上，我们提出了一种名为SLNAS的联邦神经架构搜索（NAS）框架。SLNAS的架构建立在三个关键组件之上：采用双编码进化算法的服务器端搜索空间生成方法、基于DARTS的联邦NAS过程以及利用Gumbel softmax结合知识蒸馏的客户端架构调整。为了验证鲁棒性，我们调整了一个框架，其中包括基于触发器优化、数据投毒和模型投毒的后门攻击，目标是模型权重和架构参数。大量实验表明，SLNAS不仅能有效对抗高级后门攻击，还能处理异构性，在各种后门攻击场景下优于防御基线。
4486.
宋晓天；谢景荣；冯玉琪；宋安迪；孙亚楠
收录于：IEEE Transactions on Computers，第01期，第1-12页，5555年，ISSN：1557-9956。
@article{11216133,
title = { DAP: Domain Adaptive Performance Predictor for Efficient Neural Architecture Search },
author = {Xiaotian Song and Jingrong Xie and Yuqi Feng and Andy Song and Yanan Sun},
url = {https://doi.ieeecomputersociety.org/10.1109/TC.2025.3624960},
doi = {10.1109/TC.2025.3624960},
issn = {1557-9956},
year = {5555},
date = {5555-10-01},
urldate = {5555-10-01},
journal = {IEEE Transactions on Computers},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Neural architecture search (NAS) aims to automatically design high-performance architectures of deep neural networks, which have shown great potential in various fields. However, the search process of NAS is computationally expensive since plenty of deep neural networks are trained to get the performance on GPUs. Performance predictors can directly estimate the performance of architectures without GPU-based training, thus can overcome this barrier. However, the construction of performance predictors requires labeling plenty of architectures sampled from the corresponding NAS search space, which is still prohibitively costly. In this paper, we propose a Domain Adaptive performance Predictor (DAP), which can construct a performance predictor based on the labeled architectures provided by existing benchmarks and then enable it to other search spaces via domain adaptive techniques. To achieve this, we first propose a domain-agnostic feature extraction method to refine the domain-invariant features of neural architectures. Then, we propose a novel embedding method to learn the shared representations of architecture operations. Experimental results demonstrate that DAP outperforms eight baselines upon six popular search spaces. Notably, we only require the search cost of 0:0002 GPU Days to find the architecture with 77:10% top-1 accuracy on ImageNet and 97:86% on CIFAR-10. In addition, we show the theoretical upper bound of the generalization error in the target search space, further illustrating the generalizability of DAP. The source code is available at https://anonymous.4open.science/r/DAP-2F1F/.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
神经架构搜索（NAS）旨在自动设计深度神经网络的高性能架构，在各个领域显示出巨大的潜力。然而，NAS的搜索过程计算成本高昂，因为需要训练大量的深度神经网络才能在GPU上获得性能。性能预测器可以直接估计架构的性能，无需基于GPU的训练，因此可以克服这一障碍。然而，性能预测器的构建需要对从相应NAS搜索空间采样的许多架构进行标记，这仍然是成本极高的。在本文中，我们提出了一种域自适应性能预测器（DAP），它可以在现有基准提供的标记架构的基础上构建性能预测器，然后通过域自适应技术将其应用于其他搜索空间。为此，我们首先提出了一种域无关特征提取方法来提炼神经网络架构的域不变特征。然后，我们提出了一种新颖的嵌入方法来学习架构操作的共享表示。实验结果表明，DAP在六个流行搜索空间上的性能优于八个基线。值得注意的是，我们仅需0:0002 GPU天的搜索成本即可在ImageNet上找到77:10% top-1准确率和CIFAR-10上97:86% top-1准确率的架构。此外，我们还展示了目标搜索空间中泛化误差的理论上限，进一步说明了DAP的通用性。源代码可在https://anonymous.4open.science/r/DAP-2F1F/获取。
4485.
张宇明；谢俊伟；李俊杰；范国钦
RATs-NAS：基于图卷积网络中相邻路径重定向的预测器神经架构搜索 期刊文章
收录于：IEEE Transactions on Artificial Intelligence，第1卷，第01期，第1-11页，5555年，ISSN：2691-4581。
@article{10685480,
title = { RATs-NAS: Redirection of Adjacent Trails on Graph Convolutional Networks for Predictor-based Neural Architecture Search },
author = {Yu-Ming Zhang and Jun-Wei Hsieh and Chun-Chieh Lee and Kuo-Chin Fan},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2024.3465433},
doi = {10.1109/TAI.2024.3465433},
issn = {2691-4581},
year = {5555},
date = {5555-09-01},
urldate = {5555-09-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-11},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Manually designed CNN architectures like VGG, ResNet, DenseNet, and MobileNet have achieved high performance across various tasks, but design them is time-consuming and costly. Neural Architecture Search (NAS) automates the discovery of effective CNN architectures, reducing the need for experts. However, evaluating candidate architectures requires significant GPU resources, leading to the use of predictor-based NAS, such as graph convolutional networks (GCN), which is the popular option to construct predictors. However, we discover that, even though the ability of GCN mimics the propagation of features of real architectures, the binary nature of the adjacency matrix limits its effectiveness. To address this, we propose Redirection of Adjacent Trails (RATs), which adaptively learns trail weights within the adjacency matrix. Our RATs-GCN outperform other predictors by dynamically adjusting trail weights after each graph convolution layer. Additionally, the proposed Divide Search Sampling (DSS) strategy, based on the observation of cell-based NAS that architectures with similar FLOPs perform similarly, enhances search efficiency. Our RATs-NAS, which combine RATs-GCN and DSS, shows significant improvements over other predictor-based NAS methods on NASBench-101, NASBench-201, and NASBench-301.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
VGG、ResNet、DenseNet和MobileNet等手动设计的CNN架构在各种任务中都取得了高性能，但设计它们耗时且成本高昂。神经架构搜索（NAS）自动化了有效CNN架构的发现，减少了对专家的需求。然而，评估候选架构需要大量的GPU资源，导致使用基于预测器的NAS，例如图卷积网络（GCN），这是构建预测器的流行选择。但是，我们发现，尽管GCN具有模拟真实架构特征传播的能力，但邻接矩阵的二进制性质限制了其有效性。为了解决这个问题，我们提出了相邻路径重定向（RATs），它自适应地学习邻接矩阵内的路径权重。我们的RATs-GCN通过在每个图卷积层之后动态调整路径权重，优于其他预测器。此外，基于细胞NAS中具有相似FLOPs的架构表现相似的观察，提出的划分搜索采样（DSS）策略提高了搜索效率。我们的RATs-NAS结合了RATs-GCN和DSS，在NASBench-101、NASBench-201和NASBench-301上相对于其他基于预测器的NAS方法显示出显著的改进。
4484.
陈X；杨C.
收录于：IEEE Micro，第01期，第1-12页，5555年，ISSN：1937-4143。
@article{10551739,
title = {CIMNet: Joint Search for Neural Network and Computing-in-Memory Architecture},
author = {X. Chen and C. Yang},
url = {https://www.computer.org/csdl/magazine/mi/5555/01/10551739/1XyKBmSlmPm},
doi = {10.1109/MM.2024.3409068},
issn = {1937-4143},
year = {5555},
date = {5555-06-01},
urldate = {5555-06-01},
journal = {IEEE Micro},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Computing-in-memory (CIM) architecture has been proven to effectively transcend the memory wall bottleneck, expanding the potential of low-power and high-throughput applications such as machine learning. Neural architecture search (NAS) designs ML models to meet a variety of accuracy, latency, and energy constraints. However, integrating CIM into NAS presents a major challenge due to additional simulation overhead from the non-ideal characteristics of CIM hardware. This work introduces a quantization and device aware accuracy predictor that jointly scores quantization policy, CIM architecture, and neural network architecture, eliminating the need for time-consuming simulations in the search process. We also propose reducing the search space based on architectural observations, resulting in a well-pruned search space customized for CIM. These allow for efficient exploration of superior combinations in mere CPU minutes. Our methodology yields CIMNet, which consistently improves the trade-off between accuracy and hardware efficiency on benchmarks, providing valuable architectural insights.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
内存计算（CIM）架构已被证明能有效克服内存墙瓶颈，扩展了机器学习等低功耗、高吞吐量应用的潜力。神经架构搜索（NAS）旨在设计满足各种精度、延迟和能耗限制的机器学习模型。然而，由于CIM硬件非理想特性带来的额外仿真开销，将CIM集成到NAS中带来了重大挑战。本研究引入了一种量化和设备感知的精度预测器，该预测器联合评估量化策略、CIM架构和神经网络架构，从而消除了搜索过程中耗时的仿真需求。我们还提出了基于架构观察来缩小搜索空间的方法，从而得到一个针对CIM定制的精简搜索空间。这些方法使得在短短数分钟的CPU时间内高效探索卓越组合成为可能。我们的方法产生了CIMNet，它在基准测试中持续改进了精度和硬件效率之间的权衡，提供了宝贵的架构见解。
4483.
Lv, Hao; Zhang, Lei; Wang, Ying
In-situ NAS: 跨硬件平台的即插即用神经架构搜索框架 期刊文章
收录于: IEEE Transactions on Computers, no. 01, pp. 1-14, 5555, ISSN: 1557-9956。
@article{11003207,
title = { In-situ NAS: A Plug-and-Search Neural Architecture Search framework across hardware platforms },
author = {Hao Lv and Lei Zhang and Ying Wang},
url = {https://doi.ieeecomputersociety.org/10.1109/TC.2025.3569161},
doi = {10.1109/TC.2025.3569161},
issn = {1557-9956},
year = {5555},
date = {5555-05-01},
urldate = {5555-05-01},
journal = {IEEE Transactions on Computers},
number = {01},
pages = {1-14},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Hardware-aware Neural Architecture Search (HW-NAS) has garnered significant research interest due to its ability to automate the design of neural networks for various hardware platforms. Prevalent HW-NAS frameworks often use fast predictors to estimate network performance, bypassing the time-consuming actual profiling step. However, the resource-intensive nature of building these predictors and their accuracy limitations hinder their practical use in diverse deployment scenarios. In response, we emphasize the indispensable role of actual profiling in HW-NAS and explore efficiency optimization possibilities within the HW-NAS framework. We provide a systematic analysis of profiling overhead in HW-NAS and identify many redundant and unnecessary operations during the search phase. We then optimize the workflow and present Insitu NAS, which leverages similarity features and exploration history to eliminate redundancy and improve runtime efficiency. In-situ NAS also offers simplified interfaces to ease the user’s effort in managing the complex device-dependent profiling flow, enabling plug-and-search functionality across diverse hardware platforms. Experimental results show that In-situ NAS achieves an average 10x speedup across different hardware platforms while reducing the search overhead by 8x compared to predictor-based approaches in various deployment scenarios. Additionally, In-situ NAS consistently discovers networks with better accuracy (about 1.5%) across diverse hardware platforms compared to predictor-based NAS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
硬件感知神经架构搜索（HW-NAS）因其能够自动化设计用于各种硬件平台的神经网络而引起了广泛的研究兴趣。流行的HW-NAS框架通常使用快速预测器来估计网络性能，从而绕过耗时的实际分析步骤。然而，构建这些预测器的资源密集性及其精度限制阻碍了它们在多样化部署场景中的实际应用。为此，我们强调了实际分析在HW-NAS中不可或缺的作用，并探索了HW-NAS框架内的效率优化可能性。我们对HW-NAS中的分析开销进行了系统分析，并识别了搜索阶段的许多冗余和不必要的操作。然后，我们优化了工作流程，并提出了Insitu NAS，它利用相似性特征和探索历史来消除冗余并提高运行时效率。In-situ NAS还提供了简化的接口，以减轻用户管理复杂设备相关分析流程的难度，从而实现跨不同硬件平台的即插即用功能。实验结果表明，与基于预测器的方法相比，In-situ NAS在不同硬件平台上平均实现了10倍的加速，同时在各种部署场景中将搜索开销降低了8倍。此外，与基于预测器的NAS相比，In-situ NAS在不同硬件平台上始终能发现具有更高精度（约1.5%）的网络。
4482.
Siddique, Ayesha; Hoque, Khaza Anuarul
可解释人工智能引导的神经架构搜索，用于近似DNN中的对抗鲁棒性 期刊文章
收录于: IEEE Transactions on Sustainable Computing, no. 01, pp. 1-15, 5555, ISSN: 2377-3782。
@article{10966055,
title = { Explainable AI-Guided Neural Architecture Search for Adversarial Robustness in Approximate DNNs },
author = {Ayesha Siddique and Khaza Anuarul Hoque},
url = {https://doi.ieeecomputersociety.org/10.1109/TSUSC.2025.3561603},
doi = {10.1109/TSUSC.2025.3561603},
issn = {2377-3782},
year = {5555},
date = {5555-04-01},
urldate = {5555-04-01},
journal = {IEEE Transactions on Sustainable Computing},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Deep neural networks are lucrative targets of adversarial attacks and approximate deep neural networks (AxDNNs) are no exception. Searching manually for adversarially robust AxDNN architectures incurs outrageous time and human effort. In this paper, we propose XAI-NAS, an explainable neural architecture search (NAS) method that leverages explainable artificial intelligence (XAI) to efficiently co-optimize the adversarial robustness and hardware efficiency of AxDNN architectures on systolic-array hardware accelerators. During the NAS process, AxDNN architectures are evolved layer-wise with heterogeneous approximate multipliers to deliver the best trade-offs between adversarial robustness, energy consumption, latency, and memory footprint. The most suitable approximate multipliers are automatically selected from an open-source Evoapprox8b library. Our extensive evaluations provide a set of Pareto optimal hardware efficient and adversarially robust solutions. For example, a Pareto-optimal DNN AxDNN for the MNIST and CIFAR-10 datasets exhibits up to 1.5× higher adversarial robustness, 2.1× less energy consumption, 4.39× reduced latency, and 2.37× low memory footprint when compared to the state-of-the-art NAS approaches.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
深度神经网络是对抗性攻击的诱人目标，近似深度神经网络（AxDNN）也不例外。手动搜索具有对抗性鲁棒性的AxDNN架构会耗费大量时间和人力。本文提出了XAI-NAS，一种可解释的神经架构搜索（NAS）方法，它利用可解释人工智能（XAI）在脉动阵列硬件加速器上高效地协同优化AxDNN架构的对抗性鲁棒性和硬件效率。在NAS过程中，AxDNN架构通过异构近似乘法器逐层演化，以在对抗性鲁棒性、能耗、延迟和内存占用之间实现最佳权衡。最合适的近似乘法器从开源的Evoapprox8b库中自动选择。我们广泛的评估提供了一组帕累托最优的硬件高效且对抗性鲁棒的解决方案。例如，对于MNIST和CIFAR-10数据集的帕累托最优DNN AxDNN，与最先进的NAS方法相比，其对抗性鲁棒性提高了高达1.5倍，能耗降低了2.1倍，延迟减少了4.39倍，内存占用降低了2.37倍。
4481.
Dong, Yukang; Pan, Fanxing; Gui, Yi; Jiang, Wenbin; Wan, Yao; Zheng, Ran; Jin, Hai
深度图神经网络的综合架构搜索 期刊文章
收录于: IEEE Transactions on Big Data, no. 01, pp. 1-15, 5555, ISSN: 2332-7790。
@article{10930718,
title = { Comprehensive Architecture Search for Deep Graph Neural Networks },
author = {Yukang Dong and Fanxing Pan and Yi Gui and Wenbin Jiang and Yao Wan and Ran Zheng and Hai Jin},
url = {https://doi.ieeecomputersociety.org/10.1109/TBDATA.2025.3552336},
doi = {10.1109/TBDATA.2025.3552336},
issn = {2332-7790},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Big Data},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
近年来，神经架构搜索（NAS）已成为一种有前途的方法，用于自动发现深度图神经网络（GNN）的优越模型架构。不同的方法关注不同类型的搜索空间。然而，由于训练深度GNN的耗时性质，现有的NAS方法往往未能充分探索多样化的搜索空间，这限制了其有效性。为了解决这个难题，我们提出了CAS-DGNN，一种用于深度GNN的新型综合架构搜索方法。它包含四种搜索空间，即聚合和更新操作的组合、不同类型的聚合操作、残差连接和超参数。为了满足这种复杂情况的需求，我们提出了一种分阶段混合搜索策略，以适应不同搜索空间的多样化特性。具体而言，我们将搜索过程分为四个阶段，利用进化算法和贝叶斯优化。同时，我们设计了两种针对残差连接的独特搜索方法（全连接搜索和初始残差搜索）来简化搜索空间，从而增强了CAS-DGNN的可扩展性。实验结果表明，与现有方法相比，CAS-DGNN在十个公共数据集上以具有竞争力的搜索成本实现了更高的精度。
4480.
Yan, J.; Liu, J.; Xu, H.; Wang, Z.; Qiao, C.
Peaches：边缘计算中结合神经架构搜索的个性化联邦学习 期刊文章
收录于: IEEE Transactions on Mobile Computing, no. 01, pp. 1-17, 5555, ISSN: 1558-0660。
@article{10460163,
title = {Peaches: Personalized Federated Learning with Neural Architecture Search in Edge Computing},
author = {J. Yan and J. Liu and H. Xu and Z. Wang and C. Qiao},
doi = {10.1109/TMC.2024.3373506},
issn = {1558-0660},
year = {5555},
date = {5555-03-01},
urldate = {5555-03-01},
journal = {IEEE Transactions on Mobile Computing},
number = {01},
pages = {1-17},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In edge computing (EC), federated learning (FL) enables numerous distributed devices (or workers) to collaboratively train AI models without exposing their local data. Most works of FL adopt a predefined architecture on all participating workers for model training. However, since workers' local data distributions vary heavily in EC, the predefined architecture may not be the optimal choice for every worker. It is also unrealistic to manually design a high-performance architecture for each worker, which requires intense human expertise and effort. In order to tackle this challenge, neural architecture search (NAS) has been applied in FL to automate the architecture design process. Unfortunately, the existing federated NAS frameworks often suffer from the difficulties of system heterogeneity and resource limitation. To remedy this problem, we present a novel framework, termed Peaches, to achieve efficient searching and training in the resource-constrained EC system. Specifically, the local model of each worker is stacked by base cell and personal cell, where the base cell is shared by all workers to capture the common knowledge and the personal cell is customized for each worker to fit the local data. We determine the number of base cells, shared by all workers, according to the bandwidth budget on the parameters server. Besides, to relieve the data and system heterogeneity, we find the optimal number of personal cells for each worker based on its computing capability. In addition, we gradually prune the search space during training to mitigate the resource consumption. We evaluate the performance of Peaches through extensive experiments, and the results show that Peaches can achieve an average accuracy improvement of about 6.29% and up to 3.97× speed up compared with the baselines.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
在边缘计算（EC）中，联邦学习（FL）使得众多分布式设备（或工作者）能够协作训练AI模型，而无需暴露其本地数据。大多数FL工作对所有参与的工作者采用预定义的架构进行模型训练。然而，由于工作者的本地数据分布在EC中差异很大，预定义的架构可能不是每个工作者的最佳选择。为每个工作者手动设计高性能架构也是不切实际的，这需要大量的人工专业知识和精力。为了应对这一挑战，神经架构搜索（NAS）已被应用于FL中，以自动化架构设计过程。不幸的是，现有的联邦NAS框架往往面临系统异构性和资源限制的困难。为了解决这个问题，我们提出了一种新颖的框架，称为Peaches，以在资源受限的EC系统中实现高效的搜索和训练。具体而言，每个工作者的本地模型由基本单元和个人单元堆叠而成，其中基本单元由所有工作者共享以捕获共同知识，而个人单元则为每个工作者定制以适应本地数据。我们根据参数服务器上的带宽预算确定所有工作者共享的基本单元数量。此外，为了缓解数据和系统异构性，我们根据每个工作者的计算能力找到最佳的个人单元数量。此外，我们在训练过程中逐步剪枝搜索空间，以减轻资源消耗。我们通过广泛的实验评估了Peaches的性能，结果表明，与基线相比，Peaches的平均精度提高了约6.29%，速度提高了3.97倍。
4479.
Sun, Genchen; Liu, Zhengkun; Gan, Lin; Su, Hang; Li, Ting; Zhao, Wenfeng; Sun, Biao
SpikeNAS-Bench: 用于脉冲神经网络架构的NAS算法基准测试 期刊文章
收录于: IEEE Transactions on Artificial Intelligence, vol. 1, no. 01, pp. 1-12, 5555, ISSN: 2691-4581。
@article{10855683,
title = { SpikeNAS-Bench: Benchmarking NAS Algorithms for Spiking Neural Network Architecture },
author = {Genchen Sun and Zhengkun Liu and Lin Gan and Hang Su and Ting Li and Wenfeng Zhao and Biao Sun},
url = {https://doi.ieeecomputersociety.org/10.1109/TAI.2025.3534136},
doi = {10.1109/TAI.2025.3534136},
issn = {2691-4581},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Artificial Intelligence},
volume = {1},
number = {01},
pages = {1-12},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {In recent years, Neural Architecture Search (NAS) has marked significant advancements, yet its efficacy is marred by the dependence on substantial computational resources. To mitigate this, the development of NAS benchmarks has emerged, offering datasets that enumerate all potential network architectures and their performances within a predefined search space. Nonetheless, these benchmarks predominantly focus on convolutional architectures, which are criticized for their limited interpretability and suboptimal hardware efficiency. Recognizing the untapped potential of Spiking Neural Networks (SNNs) — often hailed as the third generation of neural networks for their biological realism and computational thrift — this study introduces SpikeNAS-Bench. As a pioneering benchmark for SNN, SpikeNAS-Bench utilizes a cell-based search space, integrating leaky integrate-and-fire (LIF) neurons with variable thresholds as candidate operations. It encompasses 15,625 candidate architectures, rigorously evaluated on CIFAR10, CIFAR100 and Tiny-ImageNet datasets. This paper delves into the architectural nuances of SpikeNAS-Bench, leveraging various criteria to underscore the benchmark’s utility and presenting insights that could steer future NAS algorithm designs. Moreover, we assess the benchmark’s consistency through three distinct proxy types: zero-cost-based, early-stop-based, and predictor-based proxies. Additionally, the paper benchmarks seven contemporary NAS algorithms to attest to SpikeNAS-Bench’s broad applicability. We commit to providing training logs, diagnostic data for all candidate architectures, and the promise to release all code and datasets post-acceptance, aiming to catalyze further exploration and innovation within the SNN domain. SpikeNAS-Bench is open source at https://github.com/XXX (hidden for double anonymous review).},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
近年来，神经架构搜索（NAS）取得了显著进展，但其效率受限于对大量计算资源的依赖。为了缓解这一问题，NAS基准的开发应运而生，提供了在预定义搜索空间内列举所有潜在网络架构及其性能的数据集。然而，这些基准主要关注卷积架构，而卷积架构因其可解释性有限和硬件效率不佳而受到批评。认识到脉冲神经网络（SNNs）——常被称为第三代神经网络，因其生物真实性和计算节俭性而具有未开发的潜力——本研究引入了SpikeNAS-Bench。作为SNN的开创性基准，SpikeNAS-Bench利用基于细胞的搜索空间，将具有可变阈值的漏积分-火（LIF）神经元作为候选操作。它包含了15,625个候选架构，并在CIFAR10、CIFAR100和Tiny-ImageNet数据集上进行了严格评估。本文深入探讨了SpikeNAS-Bench的架构细微之处，利用各种标准强调了基准的实用性，并提出了可以指导未来NAS算法设计的见解。此外，我们通过三种不同类型的代理（基于零成本、基于提前停止和基于预测器）评估了基准的一致性。此外，本文还对七种当代NAS算法进行了基准测试，以证明SpikeNAS-Bench的广泛适用性。我们承诺提供训练日志、所有候选架构的诊断数据，并承诺在接受后发布所有代码和数据集，旨在促进SNN领域进一步的探索和创新。SpikeNAS-Bench在https://github.com/XXX（为双盲评审隐藏）开源。
4478.
Li, Changlin; Lin, Sihao; Tang, Tao; Wang, Guangrun; Li, Mingjie; Li, Zhihui; Chang, Xiaojun
BossNAS Family: 块级自监督神经架构搜索 期刊文章
收录于: IEEE Transactions on Pattern Analysis & Machine Intelligence, no. 01, pp. 1-15, 5555, ISSN: 1939-3539。
@article{10839629,
title = { BossNAS Family: Block-wisely Self-supervised Neural Architecture Search },
author = {Changlin Li and Sihao Lin and Tao Tang and Guangrun Wang and Mingjie Li and Zhihui Li and Xiaojun Chang},
url = {https://doi.ieeecomputersociety.org/10.1109/TPAMI.2025.3529517},
doi = {10.1109/TPAMI.2025.3529517},
issn = {1939-3539},
year = {5555},
date = {5555-01-01},
urldate = {5555-01-01},
journal = {IEEE Transactions on Pattern Analysis & Machine Intelligence},
number = {01},
pages = {1-15},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
abstract = {Recent advances in hand-crafted neural architectures for visual recognition underscore the pressing need to explore architecture designs comprising diverse building blocks. Concurrently, neural architecture search (NAS) methods have gained traction as a means to alleviate human efforts. Nevertheless, the question of whether NAS methods can efficiently and effectively manage diversified search spaces featuring disparate candidates, such as Convolutional Neural Networks (CNNs) and transformers, remains an open question. In this work, we introduce a novel unsupervised NAS approach called BossNAS (Block-wisely Self-supervised Neural Architecture Search), which aims to address the problem of inaccurate predictive architecture ranking caused by a large weight-sharing space while mitigating potential ranking issue caused by biased supervision. To achieve this, we factorize the search space into blocks and introduce a novel self-supervised training scheme called Ensemble Bootstrapping, to train each block separately in an unsupervised manner. In the search phase, we propose an unsupervised Population-Centric Search, optimizing the candidate architecture towards the population center. Additionally, we enhance our NAS method by integrating masked image modeling and present BossNAS++ to overcome the lack of dense supervision in our block-wise self-supervised NAS. In BossNAS++, we introduce the training technique named Masked Ensemble Bootstrapping for block-wise supernet, accompanied by a Masked Population-Centric Search scheme to promote fairer architecture selection. Our family of models, discovered through BossNAS and BossNAS++, delivers impressive results across various search spaces and datasets. Our transformer model discovered by BossNAS++ attains a remarkable accuracy of 83.2% on ImageNet with only 10.5B MAdds, surpassing DeiT-B by 1.4% while maintaining a lower computation cost. Moreover, our approach excels in architecture rating accuracy, achieving Spearman correlations of 0.78 and 0.76 on the canonical MBConv search space with ImageNet and the NATS-Bench size search space with CIFAR-100, respectively, outperforming state-of-the-art NAS methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
近年来，手工设计的视觉识别神经架构的进步，凸显了探索包含多样化构建块的架构设计的迫切需求。同时，神经架构搜索（NAS）方法作为减轻人工工作量的手段越来越受到关注。然而，NAS方法能否高效、有效地管理具有不同候选（如卷积神经网络（CNN）和Transformer）的多样化搜索空间，仍然是一个悬而未决的问题。在这项工作中，我们引入了一种新颖的无监督NAS方法，称为BossNAS（块级自监督神经架构搜索），旨在解决由于大型权重共享空间导致的不准确预测架构排名问题，同时缓解由偏向监督引起的潜在排名问题。为此，我们将搜索空间分解为块，并引入了一种名为Ensemble Bootstrapping的新型自监督训练方案，以无监督方式单独训练每个块。在搜索阶段，我们提出了一种无监督的以种群为中心的搜索方法，将候选架构优化到种群中心。此外，我们通过集成掩码图像建模来增强我们的NAS方法，并提出了BossNAS++，以克服我们块级自监督NAS中缺乏密集监督的问题。在BossNAS++中，我们引入了名为Masked Ensemble Bootstrapping的块级超网训练技术，并辅以Masked Population-Centric Search方案，以促进更公平的架构选择。我们通过BossNAS和BossNAS++发现的模型家族在各种搜索空间和数据集上都取得了令人印象深刻的结果。BossNAS++发现的Transformer模型在ImageNet上以仅10.5B MAdds达到了83.2%的显着精度，超过DeiT-B 1.4%，同时保持了较低的计算成本。此外，我们的方法在架构评级精度方面表现出色，在ImageNet的典型MBConv搜索空间和CIFAR-100的NATS-Bench大小搜索空间上分别达到了0.78和0.76的Spearman相关性，优于最先进的NAS方法。
2026
4477.
Wu, Yu; Fan, Hailong; Zhou, Zekun; Ying, Weiqin; Wu, Zhenfeng; Zhao, Jinhuai; Yu, Fahong
具有三阶段加速的联邦渐进式进化神经架构搜索，用于隐私保护医学图像分割 期刊文章
收录于: Applied Soft Computing, vol. 186, pp. 114146, 2026, ISSN: 1568-4946。
@article{WU2026114146,
title = {Federated progressive evolutionary neural architecture search with three-phase acceleration for privacy-preserving medical image segmentation},
author = {Yu Wu and Hailong Fan and Zekun Zhou and Weiqin Ying and Zhenfeng Wu and Jinhuai Zhao and Fahong Yu},
url = {https://www.sciencedirect.com/science/article/pii/S1568494625014590},
doi = {https://doi.org/10.1016/j.asoc.2025.114146},
issn = {1568-4946},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Applied Soft Computing},
volume = {186},
pages = {114146},
abstract = {Deep neural networks (DNNs) for medical image segmentation often require private data from multiple medical institutions, but privacy concerns limit data sharing. Federated learning (FL) offers a viable alternative to train networks across distributed private data. However, predefined network architectures for FL are often not optimal and require extensive manual tuning. Traditional neural architecture search (NAS) methods are unsuitable for FL due to the risk of privacy disclosure and high communication and evaluation costs. This paper proposes a federated progressive evolutionary NAS (FP-ENAS) method with three-phase acceleration to automatically generate neural architectures for privacy-preserving medical image segmentation. FP-ENAS constructs a tailored supernet and search space by enhancing U-Net++ with depthwise separable convolutions and adaptable skip connections. Then, FP-ENAS leverages a multi-objective evolutionary algorithm to search for its subnets with higher segmentation accuracy and fewer parameters. FP-ENAS adopts a three-phase hierarchical progressive acceleration mechanism to significantly reduce communication and evaluation costs of federated NAS. Specifically, the mechanism employs a federated weight sharing strategy, federated low-fidelity evaluation strategy, and federated online surrogate prediction strategy in the early, middle, and advanced phases, respectively, to balance the efficiency and accuracy of evaluations. This method accelerates the search process while maintaining high performance and ensuring privacy protection. Experimental results on the retinal vessel, brain tumor and skin lesion segmentation datasets show that FP-ENAS automatically and efficiently generates multiple excellent architectures with different sizes. They outperform several popular hand-crafted networks in terms of segmentation accuracy and model size for privacy-preserving medical image segmentation. Compared with the standard U-Net, the architectures generated by FP-ENAS yield the improvements of up to 2.27 and 1.94 % points respectively in the DICE score on the retinal vessel and brain tumor datasets, while requiring 31.1 % and 17.7 % fewer parameters.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
用于医学图像分割的深度神经网络（DNN）通常需要来自多个医疗机构的私人数据，但隐私问题限制了数据共享。联邦学习（FL）提供了一种可行的替代方案，可以在分布式私有数据上训练网络。然而，FL的预定义网络架构通常不是最优的，需要大量的手动调整。传统的神经架构搜索（NAS）方法不适用于FL，因为存在隐私泄露的风险以及高昂的通信和评估成本。本文提出了一种具有三阶段加速的联邦渐进式进化NAS（FP-ENAS）方法，用于自动生成隐私保护医学图像分割的神经架构。FP-ENAS通过使用深度可分离卷积和可适应跳跃连接增强U-Net++来构建定制的超网和搜索空间。然后，FP-ENAS利用多目标进化算法搜索具有更高分割精度和更少参数的子网。FP-ENAS采用三阶段分层渐进式加速机制，以显著降低联邦NAS的通信和评估成本。具体来说，该机制在早期、中期和高级阶段分别采用联邦权重共享策略、联邦低保真度评估策略和联邦在线代理预测策略，以平衡评估效率和精度。该方法在保持高性能和确保隐私保护的同时加速了搜索过程。在视网膜血管、脑肿瘤和皮肤病变分割数据集上的实验结果表明，FP-ENAS自动高效地生成了多个不同尺寸的优秀架构。在隐私保护医学图像分割方面，它们在分割精度和模型大小上优于几种流行的手工设计网络。与标准U-Net相比，FP-ENAS生成的架构在视网膜血管和脑肿瘤数据集上的DICE分数分别提高了高达2.27和1.94个百分点，同时所需的参数分别减少了31.1%和17.7%。
4476.
Xu, Qianao; Hu, Ziyu; Sun, Hao; Wei, Lixin; Dai, Yan; Zhang, Kexin
DDMM：多输出树突神经元模型的双准则动态迁移和多目标架构搜索 期刊文章
收录于: Expert Systems with Applications, vol. 299, pp. 130069, 2026, ISSN: 0957-4174。
@article{XU2026130069,
title = {DDMM: Dual-criterion dynamic migration and multi-objective architecture search for the multi-output dendritic neuron model},
author = {Qianao Xu and Ziyu Hu and Hao Sun and Lixin Wei and Yan Dai and Kexin Zhang},
url = {https://www.sciencedirect.com/science/article/pii/S0957417425036851},
doi = {https://doi.org/10.1016/j.eswa.2025.130069},
issn = {0957-4174},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Expert Systems with Applications},
volume = {299},
pages = {130069},
abstract = {The multi-input multi-output dendritic neuron model, as an artificial neural network, has achieved remarkable results in handling nonlinear classification problems. However, it not only requires training a filtering matrix for pruning redundant dendrites but also needs to optimize structural parameters. Therefore, Multi-output dendritic neuron model is designed which retains the original soma layer from the dendritic neuron mode and discards the filtering matrix, enabling holistic multi-objective optimization of the model. To address insufficient population diversity and overfitting tendency in model optimization, a dual-criterion dynamic migration multi-objective evolutionary algorithm is proposed. In this algorithm, the original population is divided into three subpopulations, and computational resources are allocated based on two optimization criteria. Then the penalty mechanism and migration strategy are employed to enhance population diversity and exchange elite individuals across subpopulations. The introduction of the multi-output dendritic neuron model architecture converts the multi-output dendritic model structural search as a large-scale multi-objective optimization problem, and the dual-criterion dynamic migration multi-objective evolutionary algorithm is specifically designed to address Experimental results on 11 public datasets demonstrate that the proposed algorithm achieves improvements of 27.48 % in HV, 26.33 % in IGD, and 6.9 % in classification accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
多输入多输出树突神经元模型作为一种人工神经网络，在处理非线性分类问题上取得了显著成果。然而，它不仅需要训练一个过滤矩阵来修剪冗余树突，还需要优化结构参数。因此，本文设计了多输出树突神经元模型，它保留了树突神经元模型的原始胞体层并摒弃了过滤矩阵，从而实现了模型的整体多目标优化。为了解决模型优化中种群多样性不足和过拟合的倾向，提出了一种双准则动态迁移多目标进化算法。在该算法中，原始种群被分为三个子种群，并根据两个优化准则分配计算资源。然后，采用惩罚机制和迁移策略来增强种群多样性并在子种群之间交换精英个体。多输出树突神经元模型的引入将多输出树突模型的结构搜索转化为一个大规模的多目标优化问题，并且双准则动态迁移多目标进化算法专门设计用于解决该问题。在11个公共数据集上的实验结果表明，所提出的算法在HV上提高了27.48%，在IGD上提高了26.33%，在分类精度上提高了6.9%。
4475.
Li, Qiuying; Chen, Zhixiang; Li, Yu; Jiang, Zhiyuan; Cao, Shan
通过梯度分数感知剪枝实现高效网络压缩 期刊文章
收录于: Neurocomputing, vol. 660, pp. 131870, 2026, ISSN: 0925-2312。
@article{LI2026131870,
title = {Efficient network compression via gradient-score aware pruning},
author = {Qiuying Li and Zhixiang Chen and Yu Li and Zhiyuan Jiang and Shan Cao},
url = {https://www.sciencedirect.com/science/article/pii/S0925231225025421},
doi = {https://doi.org/10.1016/j.neucom.2025.131870},
issn = {0925-2312},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Neurocomputing},
volume = {660},
pages = {131870},
abstract = {Convolutional neural networks (CNNs) have demonstrated significant achievements in the field of computer vision, yet their high computational demands restrict practical applications. Current pruning methods seek to mitigate this issue, which however often rely on heuristic manual approaches, encountering challenges in maintaining both significant model compression and accuracy. To address the above issues, a fast neural architecture search pruning (FNP) technique is proposed in this paper. Firstly, an importance matrix (IM) based preprocessing stage efficiently removes redundant structures by considering both weight importance and computational complexity, providing a compact baseline for subsequent pruning. Secondly, we adapt fast genetic algorithms (FGA) to identify optimally pruned model configurations. Furthermore, to accelerate the search process, we utilize a zero-shot learning approach to estimate model performance with the score of the frame (SoF), which is a gradient-based score. Compared with state-of-the-art (SOTA) pruning techniques, FNP demonstrates superior performance in terms of search duration and compression ratio. On the CIFAR-10 dataset, our method removes 95.24 % of the parameters in VGG-16 while achieving a 0.72 % accuracy improvement compared with the baseline. On the ImageNet dataset, we prune 68.98 % of the parameters in ResNet-50 and obtain a 1.2 % accuracy improvement compared with state-of-the-art (SOTA) approaches, while reducing the search time by 98.94 %. The code is available at https://github.com/aqiu1222/FNP.git},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
卷积神经网络（CNNs）在计算机视觉领域取得了显著成就，但其高计算需求限制了实际应用。当前的剪枝方法旨在缓解这一问题，然而它们通常依赖启发式手动方法，在保持显著模型压缩和精度方面面临挑战。为了解决上述问题，本文提出了一种快速神经架构搜索剪枝（FNP）技术。首先，基于重要性矩阵（IM）的预处理阶段通过同时考虑权重重要性和计算复杂性，有效地移除冗余结构，为后续剪枝提供紧凑的基线。其次，我们采用快速遗传算法（FGA）来识别最优剪枝模型配置。此外，为了加速搜索过程，我们利用零样本学习方法通过基于梯度的分数（SoF）来估计模型性能。与最先进（SOTA）的剪枝技术相比，FNP在搜索持续时间和压缩率方面表现出卓越的性能。在CIFAR-10数据集上，我们的方法在VGG-16中移除了95.24%的参数，同时比基线提高了0.72%的精度。在ImageNet数据集上，我们剪枝了ResNet-50中68.98%的参数，与最先进（SOTA）方法相比，精度提高了1.2%，同时搜索时间减少了98.94%。代码可在https://github.com/aqiu1222/FNP.git获取。
4474.
Clercq, Johannes De; Pillay, Nelishia
收录于: Neural Networks, vol. 195, pp. 108259, 2026, ISSN: 0893-6080。
@article{DECLERCQ2026108259,
title = {A selection perturbative hyper-heuristic for neural architecture search},
author = {Johannes De Clercq and Nelishia Pillay},
url = {https://www.sciencedirect.com/science/article/pii/S0893608025011402},
doi = {https://doi.org/10.1016/j.neunet.2025.108259},
issn = {0893-6080},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Neural Networks},
volume = {195},
pages = {108259},
abstract = {Neural architecture search explores the architecture space, referred to as the design spaces, to find an architecture that produces good results. Various approaches, such as genetic algorithms, are usually used to explore this space. This study investigates exploring an alternative space, namely, the heuristic space using a hyper-heuristic to indirectly explore the design space. The study introduces the concept of a NAS operator space (NOS). A single point selection perturbative hyper-heuristic(SPHH-NAS) explores a heuristic space that maps to the NOS which then maps to the design space. A choice function is used for heuristic selection and the Adaptive Improvement Limited Target Acceptance (AILTA) for move acceptance. It is anticipated that indirectly searching the design space will facilitate reaching areas of the search space that could not be reached by searching the space directly. SPHH-NAS was evaluated on three NAS benchmark sets, namely, NAS-101, NAS-201 and NAS-301. In addition to this the approach is evaluated on two real-world datasets. SPHH-NAS was found to outperform majority of the previous approaches used to solve these problems. In addition to this SPHH-NAS resulted in a reduction in computational cost.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
神经架构搜索探索架构空间，即设计空间，以找到产生良好结果的架构。通常使用各种方法，例如遗传算法来探索这个空间。本研究调查了使用超启发式方法探索替代空间，即启发式空间，以间接探索设计空间。本研究引入了NAS操作符空间（NOS）的概念。一个单点选择扰动超启发式（SPHH-NAS）探索一个映射到NOS的启发式空间，然后NOS映射到设计空间。选择函数用于启发式选择，自适应改进有限目标接受（AILTA）用于移动接受。预计间接搜索设计空间将有助于到达通过直接搜索无法到达的搜索空间区域。SPHH-NAS在三个NAS基准集上进行了评估，即NAS-101、NAS-201和NAS-301。此外，该方法还在两个真实世界数据集上进行了评估。结果发现SPHH-NAS优于大多数以前用于解决这些问题的方法。此外，SPHH-NAS还降低了计算成本。
4473.
Ye, Tingyu; Zhang, Ping; Zeng, Hongliang; Wang, Jiahua
结合二元人工蜂群算法的多目标神经架构搜索用于动态手势识别 期刊文章
收录于: Expert Systems with Applications, vol. 299, pp. 130128, 2026, ISSN: 0957-4174。
@article{YE2026130128,
title = {Multi-objective neural architecture search combining binary artificial bee colony algorithm for dynamic hand gesture recognition},
author = {Tingyu Ye and Ping Zhang and Hongliang Zeng and Jiahua Wang},
url = {https://www.sciencedirect.com/science/article/pii/S0957417425037431},
doi = {https://doi.org/10.1016/j.eswa.2025.130128},
issn = {0957-4174},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Expert Systems with Applications},
volume = {299},
pages = {130128},
abstract = {Designing neural network architectures for dynamic hand gesture recognition (DHGR) requires a careful balance between recognition accuracy and computational efficiency, particularly for real-time interaction on mobile or embedded platforms. To address this challenge, we propose MONAS_ABC, a multi-objective neural architecture search (NAS) framework based on the binary artificial bee colony algorithm. The framework incorporates tailored strategies across the employed, onlooker, and scout bee phases, enabling efficient exploration in a MobileNetV2-inspired lightweight search space through binary-encoded representations. We first evaluate MONAS_ABC on two multi-objective optimization benchmarks, C10/MOP and IN1K/MOP, where it demonstrates superior convergence behavior and solution diversity compared to conventional approaches. We further apply the framework to two real-world DHGR datasets: EgoGesture and NvGesture. On EgoGesture, MONAS_ABC achieves a Top-1 accuracy of 93.17 % with only 0.76G FLOPs and 2.05 million parameters, significantly outperforming established 3D CNN models such as C3D and TSM in both accuracy and resource consumption. Comparable performance is observed on NvGesture, confirming the generalizability of the discovered architectures. These results collectively demonstrate that MONAS_ABC effectively discovers scalable and efficient architectures, capable of balancing performance and complexity across both generic optimization problems and practical DHGR scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
为动态手势识别（DHGR）设计神经网络架构需要在识别精度和计算效率之间取得谨慎的平衡，特别是对于移动或嵌入式平台上的实时交互。为了解决这一挑战，我们提出了MONAS_ABC，一个基于二元人工蜂群算法的多目标神经架构搜索（NAS）框架。该框架在雇佣蜂、观察蜂和侦察蜂阶段融入了定制策略，通过二元编码表示在受MobileNetV2启发的轻量级搜索空间中实现高效探索。我们首先在C10/MOP和IN1K/MOP这两个多目标优化基准上评估MONAS_ABC，结果表明它比传统方法具有更优越的收敛行为和解决方案多样性。我们进一步将该框架应用于两个真实的DHGR数据集：EgoGesture和NvGesture。在EgoGesture上，MONAS_ABC以仅0.76G FLOPs和2.05百万参数实现了93.17%的Top-1精度，在精度和资源消耗方面均显著优于C3D和TSM等成熟的3D CNN模型。在NvGesture上也观察到可比的性能，证实了所发现架构的泛化能力。这些结果共同表明，MONAS_ABC能够有效地发现可扩展且高效的架构，能够在通用优化问题和实际DHGR场景中平衡性能和复杂性。
4472.
Lin, Kezhen; Zhang, Yu; Hu, Wang; Wang, Heng; Hu, Junjie
编码器驱动的动态采样NAS，用于重拍焊缝X射线照片检索中的关键区域再识别 期刊文章
收录于: Applied Soft Computing, vol. 186, pp. 114098, 2026, ISSN: 1568-4946。
@article{LIN2026114098,
title = {Encoder-driven dynamically sampling NAS for key region re-identification in re-shot welding radiographs retrieval},
author = {Kezhen Lin and Yu Zhang and Wang Hu and Heng Wang and Junjie Hu},
url = {https://www.sciencedirect.com/science/article/pii/S1568494625014115},
doi = {https://doi.org/10.1016/j.asoc.2025.114098},
issn = {1568-4946},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Applied Soft Computing},
volume = {186},
pages = {114098},
abstract = {In non-destructive testing, the retrieval of re-shot welding radiographs aims to curb fraudulent practices by preventing the substitution of defective welds with re-shot qualified radiographs. The comparison of weld features is complicated due to changes in camera angles and shooting parameters. A key region re-identification method for re-shot welding radiograph retrieval is introduced in this paper. This approach re-identifies robust key regions across different shooting positions, then compares and arranges them based on their spatial positioning, proving effective for retrieving re-shot welding radiographs. To further enhance key region metric, neural architecture search (NAS) is used to find network architectures suitable for feature extraction from welding radiographs. For network encoding, a posterior tuned strategy is proposed, adjusting the decoder’s output distribution using its posterior distribution to ensure uniformity and boundary conditions in latent space mapping. For network evaluation, an efficient dynamically sampling NAS (DS-NAS) framework is introduced, including an improved triplet loss function, the intra-entity perception triplet loss (IePT loss), and an effective method for selecting hard samples. DS-NAS dynamically adjusts the difficulty of sample selection based on model performance, improving the efficiency and accuracy of network architecture evaluation in NAS. The proposed DS-NAS framework searched for a high-performing network within 3.6 GPU-days. The resulting architecture achieved a significantly superior 69.66 mAP on the key region retrieval dataset, far surpassing the baseline. Furthermore, when applied to the re-shot welding radiograph retrieval dataset using the key region-based retrieval approach, it achieved 62.04 mAP, enabling reliable identification of re-shot welding radiographs.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
在无损检测中，重拍焊缝X射线照片的检索旨在通过防止用重拍合格的X射线照片替换有缺陷的焊缝来遏制欺诈行为。由于相机角度和拍摄参数的变化，焊缝特征的比较变得复杂。本文介绍了一种用于重拍焊缝X射线照片检索的关键区域再识别方法。该方法在不同拍摄位置重新识别鲁棒的关键区域，然后根据其空间位置进行比较和排列，证明对检索重拍焊缝X射线照片有效。为了进一步增强关键区域度量，使用神经架构搜索（NAS）来寻找适合从焊缝X射线照片中提取特征的网络架构。对于网络编码，提出了一种后验调整策略，利用解码器的后验分布调整其输出分布，以确保潜在空间映射中的均匀性和边界条件。对于网络评估，引入了一种高效的动态采样NAS（DS-NAS）框架，包括改进的三元组损失函数（实体内感知三元组损失IePT损失）和一种选择难样本的有效方法。DS-NAS根据模型性能动态调整样本选择难度，提高了NAS中网络架构评估的效率和准确性。所提出的DS-NAS框架在3.6个GPU天内搜索到了一个高性能网络。结果架构在关键区域检索数据集上实现了显著优越的69.66 mAP，远超基线。此外，当使用基于关键区域的检索方法应用于重拍焊缝X射线照片检索数据集时，它实现了62.04 mAP，从而能够可靠地识别重拍焊缝X射线照片。
4471.
Terin, Rodrigo Carmo; Arenas, Zochil González; Santana, Roberto
使用神经网络识别经典伊辛模型中的相变：一个神经架构搜索的视角 会议文章
收录于: Márquez, Fausto Pedro García; Hameed, Alaa Ali; Jamil, Akhtar (编辑): Pattern Recognition and Artificial Intelligence, pp. 741–756, Springer Nature Switzerland, Cham, 2026, ISBN: 978-3-031-90893-4。
@inproceedings{10.1007/978-3-031-90893-4_50,
title = {Identifying Phase Transitions in the Classical Ising Model with Neural Networks: A Neural Architecture Search Perspective},
author = {Rodrigo Carmo Terin and Zochil González Arenas and Roberto Santana},
editor = {Fausto Pedro García Márquez and Alaa Ali Hameed and Akhtar Jamil},
url = {https://link.springer.com/chapter/10.1007/978-3-031-90893-4_50},
isbn = {978-3-031-90893-4},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {Pattern Recognition and Artificial Intelligence},
pages = {741–756},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {The use of machine learning algorithms to investigate phase transitions in physical systems is a valuable way to better understand the characteristics of these systems. Neural networks have been used to extract information of phases and phase transitions directly from many-body configurations. However, one limitation of neural networks is that they require the definition of the model architecture and parameters previous to their application, and such determination is itself a difficult problem. In this paper, we investigate for the first time the relationship between the accuracy of neural networks for information of phases and the network configuration (that comprises the architecture and hyperparameters). We formulate the phase analysis as a regression task, address the question of generating data that reflects the different states of the physical system, and evaluate the performance of neural architecture search for this task. After obtaining the optimized architectures, we further implement smart data processing and analytics by means of neuron coverage metrics, assessing the capability of these metrics to estimate phase transitions. Our results identify the neuron coverage metric as promising for detecting phase transitions in physical systems.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
使用机器学习算法研究物理系统中的相变是更好地理解这些系统特性的宝贵方法。神经网络已被用于直接从多体构型中提取相和相变信息。然而，神经网络的一个局限性在于它们在应用之前需要定义模型架构和参数，而这种确定本身就是一个难题。在本文中，我们首次研究了神经网络在相信息精度与网络配置（包括架构和超参数）之间的关系。我们将相分析公式化为一个回归任务，解决了生成反映物理系统不同状态的数据的问题，并评估了神经架构搜索在该任务上的性能。在获得优化架构后，我们通过神经元覆盖度量进一步实现智能数据处理和分析，评估这些度量估计相变的能力。我们的结果表明神经元覆盖度量在检测物理系统中的相变方面具有潜力。
4470.
Neri, Ferrante; Liao, Lingzhen; Xue, Yu; Basgalupp, Márcio P.
具有回滚机制的GAN可微分架构搜索 期刊文章
收录于: Applied Soft Computing, vol. 186, pp. 114055, 2026, ISSN: 1568-4946。
@article{NERI2026114055,
title = {Differentiable architecture search for GANs with rollback mechanism},
author = {Ferrante Neri and Lingzhen Liao and Yu Xue and Márcio P. Basgalupp},
url = {https://www.sciencedirect.com/science/article/pii/S1568494625013687},
doi = {https://doi.org/10.1016/j.asoc.2025.114055},
issn = {1568-4946},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Applied Soft Computing},
volume = {186},
pages = {114055},
abstract = {Designing effective architectures for Generative Adversarial Networks (GANs) remains a challenging task due to training instability and the complexity of balancing generator and discriminator performance. While Neural Architecture Search (NAS) has shown promise in automating architecture design, existing NAS-GAN approaches often suffer from limited design flexibility and high computational demands. This paper introduces a gradient-based NAS framework, termed Differentiable Architecture Search for GANs with Rollback Mechanism (RASGAN), aimed at addressing these limitations. RASGAN incorporates a hyperparameter rollback to indirectly optimise evaluation metrics such as the Inception Score (IS) and Fréchet Inception Distance (FID), leading to higher-quality generative models. Moreover, the search space integrates lightweight convolutional operations to reduce computational and storage overhead without compromising performance. On unconditional image generation tasks, the proposed method achieves competitive results: on CIFAR-10, RASGAN attains IS = 8.98 and FID = 10.31; on STL-10},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
为生成对抗网络（GAN）设计有效架构仍然是一项具有挑战性的任务，原因在于训练不稳定以及平衡生成器和判别器性能的复杂性。虽然神经架构搜索（NAS）在自动化架构设计方面显示出前景，但现有的NAS-GAN方法通常面临设计灵活性有限和计算需求高的困境。本文提出了一种基于梯度的NAS框架，名为带有回滚机制的GAN可微分架构搜索（RASGAN），旨在解决这些限制。RASGAN引入超参数回滚来间接优化评估指标，如Inception Score（IS）和Fréchet Inception Distance（FID），从而产生更高质量的生成模型。此外，搜索空间集成了轻量级卷积操作，以在不影响性能的情况下减少计算和存储开销。在无条件图像生成任务中，所提出的方法取得了具有竞争力的结果：在CIFAR-10上，RASGAN达到了IS = 8.98和FID = 10.31；在STL-10上。
4469.
Qu, Wei; Chen, Cong; Lu, Wei; Chen, Haodong; Li, Tao
迈向值得信赖和可解释的校园霸凌预测：一个NAS驱动的Shapley值解释框架 期刊文章
收录于: Neurocomputing, vol. 659, pp. 131744, 2026, ISSN: 0925-2312。
@article{QU2026131744,
title = {Towards trustworthy and interpretable prediction of school bullying: A NAS-driven framework with Shapley value explanation},
author = {Wei Qu and Cong Chen and Wei Lu and Haodong Chen and Tao Li},
url = {https://www.sciencedirect.com/science/article/pii/S0925231225024166},
doi = {https://doi.org/10.1016/j.neucom.2025.131744},
issn = {0925-2312},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Neurocomputing},
volume = {659},
pages = {131744},
abstract = {School bullying represents a critical societal challenge with lasting psychological and academic consequences for affected students. Despite recent advances in machine learning for predicting bullying behaviors, conventional models struggle to capture the complex, non-linear relationships among contributing factors, especially under the imbalanced data distributions typical of real-world bullying cases. Furthermore, the inherent opacity of Deep Neural Networks (DNNs) restricts their application in educational contexts where interpretability and actionable insights are essential. In this paper, we propose a novel automated framework that integrates Neural Architecture Search (NAS) with Shapley value-based explanation methods to jointly address performance and interpretability challenges. Our framework automatically identifies optimal DNN architectures tailored for bullying prediction, incorporating mechanisms to handle class imbalance without extensive manual tuning. To address model transparency, we employ a Shapley value analysis pipeline that systematically attributes predictions to key risk factors, offering educators and policymakers principled and quantitative insights. Extensive experiments on publicly available datasets demonstrate that our method significantly outperforms state-of-the-art baselines, achieving notable improvements in Accuracy (+2.58 %), F1-Score (+34.52 %), and AUC (+6.47 %). Importantly, the feature importance rankings from our Shapley analysis closely align with established sociological and educational theories on bullying, affirming the model’s interpretability and practical relevance. Cross-dataset validation further verifies the framework’s generalizability to broader youth behavioral risk prediction tasks. Our code is submitted at https://github.com/clsyc/Bullyingshapley.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
校园霸凌是一个关键的社会挑战，对受影响的学生造成持久的心理和学业后果。尽管机器学习在预测霸凌行为方面取得了最新进展，但传统模型难以捕捉导致因素之间复杂的非线性关系，尤其是在现实世界霸凌案例中常见的数据不平衡分布下。此外，深度神经网络（DNN）固有的不透明性限制了它们在教育环境中的应用，而在教育环境中，可解释性和可操作的见解至关重要。本文提出了一种新颖的自动化框架，该框架将神经架构搜索（NAS）与基于Shapley值的解释方法相结合，以共同解决性能和可解释性挑战。我们的框架自动识别适合霸凌预测的最佳DNN架构，并结合了处理类别不平衡的机制，无需大量手动调整。为了解决模型透明度问题，我们采用了一个Shapley值分析管道，该管道系统地将预测归因于关键风险因素，为教育工作者和政策制定者提供有原则和定量的见解。对公开数据集的广泛实验表明，我们的方法显著优于最先进的基线，在准确率（+2.58%）、F1分数（+34.52%）和AUC（+6.47%）方面取得了显着改进。重要的是，我们Shapley分析的特征重要性排名与已建立的关于霸凌的社会学和教育理论密切相关，证实了模型的可解释性和实际相关性。跨数据集验证进一步验证了该框架对更广泛的青少年行为风险预测任务的泛化能力。我们的代码已提交至https://github.com/clsyc/Bullyingshapley。
4468.
Wang, Hongzhi; Wang, Chunnan; Song, Xintong; Geng, Fei
BufferNAS: 神经架构搜索中的缓冲区池采样 期刊文章
收录于: Information Sciences, vol. 726, pp. 122731, 2026, ISSN: 0020-0255。
@article{WANG2026122731,
title = {BufferNAS: Buffer pool sampling in neural architecture search},
author = {Hongzhi Wang and Chunnan Wang and Xintong Song and Fei Geng},
url = {https://www.sciencedirect.com/science/article/pii/S0020025525008679},
doi = {https://doi.org/10.1016/j.ins.2025.122731},
issn = {0020-0255},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Information Sciences},
volume = {726},
pages = {122731},
abstract = {The existing One-shot NAS algorithms can efficiently deal with automatic neural architecture search problem, and have achieved good performance in the real applications. However, they generally adopt fixed sampling strategy or hand-crafted sampling strategy for hypernetwork training. This makes the sampling procedure inefficient reducing their performance. In this paper, we aim to solve this problem, and propose a biased sampling strategy based on buffer pool, named buffer pool neural architecture search (BufferNAS). BufferNAS aims to change the sampling frequency of the hypernetwork, so that the hypernetwork training is biased towards a better sub-network. In BufferNAS, the advantages of the excellent sub-network can be expanded, making it easier to find better neural architectures during the training and search processes. We embed our buffer sampling approach into the existing One-Shot approach, and achieve good results. Final experimental results show that BufferNAS can obtain an 97.4 % accuracy with 3.4 M parameters on CIFAR-10 dataset. By improving the sampling strategy, our method exhibited better performance on image classification tasks.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
现有的一次性NAS算法能够高效处理自动神经架构搜索问题，并在实际应用中取得了良好性能。然而，它们通常采用固定的采样策略或手工设计的采样策略进行超网络训练。这使得采样过程效率低下，降低了它们的性能。本文旨在解决这一问题，并提出了一种基于缓冲区池的偏置采样策略，名为缓冲区池神经架构搜索（BufferNAS）。BufferNAS旨在改变超网络的采样频率，使超网络训练偏向于更好的子网络。在BufferNAS中，优秀子网络的优势得以扩大，使得在训练和搜索过程中更容易找到更好的神经架构。我们将我们的缓冲区采样方法嵌入到现有的一次性方法中，并取得了良好结果。最终实验结果表明，BufferNAS在CIFAR-10数据集上能够以3.4M参数获得97.4%的准确率。通过改进采样策略，我们的方法在图像分类任务上表现出更好的性能。
4467.
Sun, Xiaoxue; Wang, Hongpeng; Song, Pei-Cheng
紧凑型免训练NAS结合交替进化博弈，用于医学图像分割 会议文章
收录于: Gee, James C.; Alexander, Daniel C.; Hong, Jaesung; Iglesias, Juan Eugenio; Sudre, Carole H.; Venkataraman, Archana; Golland, Polina; Kim, Jong Hyo; Park, Jinah (编辑): Medical Image Computing and Computer Assisted Intervention – MICCAI 2025, pp. 108–118, Springer Nature Switzerland, Cham, 2026, ISBN: 978-3-032-05325-1。
@inproceedings{10.1007/978-3-032-05325-1_11,
title = {Compact Training-Free NAS with Alternating Evolution Game for Medical Image Segmentation},
author = {Xiaoxue Sun and Hongpeng Wang and Pei-Cheng Song},
editor = {James C. Gee and Daniel C. Alexander and Jaesung Hong and Juan Eugenio Iglesias and Carole H. Sudre and Archana Venkataraman and Polina Golland and Jong Hyo Kim and Jinah Park},
url = {https://link.springer.com/chapter/10.1007/978-3-032-05325-1_11},
isbn = {978-3-032-05325-1},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {Medical Image Computing and Computer Assisted Intervention – MICCAI 2025},
pages = {108–118},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Neural Architecture Search (NAS) has shown significant potential in designing deep neural networks for medical image segmentation. However, even emerging training-free NAS frameworks often incur substantial computational costs and lengthy search times. To address the critical challenges of computational efficiency and architecture interpretability, the paper proposes a compact training-free NAS framework based on an Alternating Evolution Game (AEG-cTFNAS). The proposed method alternates the search and contribution evaluation of the encoder and decoder within the UNet architecture via alternating games. It employs a truncated normal distribution for compact encoding, sampling, and updating to minimize computational overhead, while Bayesian inference is utilized to estimate the contribution of each block, adaptively adjusting the search strategy and facilitating process visualization. Experimental results on two benchmark datasets reveal that AEG-cTFNAS outperforms both manually designed architectures and NAS-based algorithms, underscoring its efficacy and potential on medical image segmentation. Code is available at https://github.com/spcity/AEG-cTFNAS.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
神经架构搜索（NAS）在设计用于医学图像分割的深度神经网络方面显示出巨大潜力。然而，即使是新兴的免训练NAS框架也常常产生大量的计算成本和漫长的搜索时间。为了解决计算效率和架构可解释性的关键挑战，本文提出了一种基于交替进化博弈的紧凑型免训练NAS框架（AEG-cTFNAS）。所提出的方法通过交替博弈在UNet架构中交替搜索和评估编码器和解码器的贡献。它采用截断正态分布进行紧凑编码、采样和更新，以最小化计算开销，同时利用贝叶斯推断估计每个块的贡献，自适应调整搜索策略并促进过程可视化。在两个基准数据集上的实验结果表明，AEG-cTFNAS优于手动设计架构和基于NAS的算法，突出了其在医学图像分割方面的功效和潜力。代码可在https://github.com/spcity/AEG-cTFNAS获取。
4466.
Pandala, Madhavi Latha; Periyanayagi, S.
基于神经架构搜索特征学习的皮肤癌诊断最优可解释视觉Transformer框架 期刊文章
收录于: Biomedical Signal Processing and Control, vol. 112, pp. 108723, 2026, ISSN: 1746-8094。
@article{PANDALA2026108723,
title = {Optimal explainable vision transformer framework for skin cancer diagnosis with neural architecture search feature learning},
author = {Madhavi Latha Pandala and S. Periyanayagi},
url = {https://www.sciencedirect.com/science/article/pii/S1746809425012340},
doi = {https://doi.org/10.1016/j.bspc.2025.108723},
issn = {1746-8094},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Biomedical Signal Processing and Control},
volume = {112},
pages = {108723},
abstract = {Skin cancer is one of the most prevalent and life-threatening diseases worldwide, making early and accurate detection crucial for improving patient survival rates. Traditional diagnostic methods rely on manual examination by dermatologists, which is subjective and time-consuming. To address these challenges, this research presents an advanced Optimal XAI based Skin Cancer Classification Network (OXAI-SCC-Net) framework for automated skin cancer detection and classification. The proposed methodology integrates multiple novel techniques to enhance accuracy and robustness. Initially, a Neural Architecture Search-Large Network (NASL-Net) is employed for feature extraction, leveraging automated deep-learning architecture search to optimize feature learning. To tackle class imbalance, a Support Vector Machine-Adopted Synthetic Oversampling Technique (SSOT) is utilized, which improves upon Synthetic Minority Oversampling Technic (SMOTE) by generating synthetic samples based on Support Vector Machine (SVM) decision boundaries, ensuring a balanced dataset. Further, Hippopotamus Optimization Algorithm with Explainable Artificial Intelligence (HOA-XAI) is applied for feature selection, reducing computational complexity by selecting the most informative features while minimizing redundant ones. Finally, a Vison Transformer Convolutional Neural Network (VT-CNN) classifier is trained on the optimized dataset to classify skin lesions into different categories. The proposed OXAI-SCC-Net method achieved an accuracy of 99.12%, with precision, recall, and F1-score each at 99.13% on ISIC-2019 dataset. This indicates highly consistent and reliable performance across all evaluation metrics compared to state-of-art approaches.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
皮肤癌是全球最流行和危及生命的疾病之一，早期准确的检测对于提高患者生存率至关重要。传统的诊断方法依赖皮肤科医生的手动检查，既主观又耗时。为了解决这些挑战，本研究提出了一种先进的基于最优XAI的皮肤癌分类网络（OXAI-SCC-Net）框架，用于自动化皮肤癌检测和分类。所提出的方法集成了多种新颖技术以提高准确性和鲁棒性。最初，采用神经架构搜索-大型网络（NASL-Net）进行特征提取，利用自动化深度学习架构搜索来优化特征学习。为解决类别不平衡问题，采用支持向量机-自适应合成过采样技术（SSOT），该技术通过基于支持向量机（SVM）决策边界生成合成样本，改进了合成少数类过采样技术（SMOTE），确保了数据集的平衡。此外，应用基于可解释人工智能的河马优化算法（HOA-XAI）进行特征选择，通过选择信息量最大的特征同时最小化冗余特征，降低了计算复杂度。最后，在优化后的数据集上训练视觉Transformer卷积神经网络（VT-CNN）分类器，将皮肤病变分类为不同类别。所提出的OXAI-SCC-Net方法在ISIC-2019数据集上实现了99.12%的准确率，精确率、召回率和F1分数均为99.13%。这表明与最先进的方法相比，所有评估指标都具有高度一致和可靠的性能。
4465.
Liu, Xuncheng; Zhang, Weizhan; Yan, Caixia; Wang, Zhiwen; Du, Haipeng
基于自动进化神经架构搜索的高效移动端实时视频超分辨率 会议文章
收录于: Senn, Walter; Sanguineti, Marcello; Saudargiene, Ausra; Tetko, Igor V.; Villa, Alessandro E. P.; Jirsa, Viktor; Bengio, Yoshua (编辑): Artificial Neural Networks and Machine Learning – ICANN 2025, pp. 86–97, Springer Nature Switzerland, Cham, 2026, ISBN: 978-3-032-04546-1。
@inproceedings{10.1007/978-3-032-04546-1_8,
title = {Efficient Real-Time On-Mobile Video Super-Resolution with Automatic Evolutionary Neural Architecture Search},
author = {Xuncheng Liu and Weizhan Zhang and Caixia Yan and Zhiwen Wang and Haipeng Du},
editor = {Walter Senn and Marcello Sanguineti and Ausra Saudargiene and Igor V. Tetko and Alessandro E. P. Villa and Viktor Jirsa and Yoshua Bengio},
url = {https://link.springer.com/chapter/10.1007/978-3-032-04546-1_8},
isbn = {978-3-032-04546-1},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2025},
pages = {86–97},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Real-time Video Super-Resolution (VSR) on mobile devices requires balancing sub-33ms latency with quality preservation – a dual challenge that existing NAS methods fail to address due to restrictive search spaces and unproven convergence. We propose an evolutionary NAS framework with three key innovations: (1) An Almost Sure Strong (A.S.S.)-convergent Genetic Algorithm with theoretical guarantees; (2) A bidirectional gene-architecture mapping encoding topological and parametric interdependencies; (3) Automated gene-to-model compilation through repair-reduction rules. Our hardware-aware implementation achieves state-of-the-art performance (+111.8% composite score) on the REDS dataset while reducing latency by 2$$backslashtimes $$×compared to baseline architectures. The convergence-proven GA demonstrates superior optimization stability over conventional NAS approaches, establishing new Pareto frontiers for mobile VSR deployments.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
移动设备上的实时视频超分辨率（VSR）需要在33毫秒以下的延迟与质量保持之间取得平衡——这是现有NAS方法由于限制性搜索空间和未经证实的收敛性而未能解决的双重挑战。我们提出了一个具有三项关键创新的进化NAS框架：（1）具有理论保证的几乎必然强（A.S.S.）收敛遗传算法；（2）编码拓扑和参数相互依赖性的双向基因-架构映射；（3）通过修复-减少规则实现基因到模型的自动化编译。我们的硬件感知实现达到了REDES数据集上的最先进性能（复合分数+111.8%），同时与基线架构相比将延迟降低了2倍。经收敛验证的GA在优化稳定性方面优于传统NAS方法，为移动VSR部署建立了新的帕累托前沿。
4464.
Chen, Pengjun; Zhu, Yanqiao; Gao, Jian; Kang, Haidong; Ma, Lianbo
MRT-NAS: 通过流形正则化提升免训练NAS性能 会议文章
收录于: Senn, Walter; Sanguineti, Marcello; Saudargiene, Ausra; Tetko, Igor V.; Villa, Alessandro E. P.; Jirsa, Viktor; Bengio, Yoshua (编辑): Artificial Neural Networks and Machine Learning – ICANN 2025, pp. 1–12, Springer Nature Switzerland, Cham, 2026, ISBN: 978-3-032-04558-4。
@inproceedings{10.1007/978-3-032-04558-4_1,
title = {MRT-NAS: Boosting Training-Free NAS via Manifold Regularization},
author = {Pengjun Chen and Yanqiao Zhu and Jian Gao and Haidong Kang and Lianbo Ma},
editor = {Walter Senn and Marcello Sanguineti and Ausra Saudargiene and Igor V. Tetko and Alessandro E. P. Villa and Viktor Jirsa and Yoshua Bengio},
url = {https://link.springer.com/chapter/10.1007/978-3-032-04558-4_1},
isbn = {978-3-032-04558-4},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2025},
pages = {1–12},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Training-free Neural Architecture Search (NAS) aims to automatically discover high-performing neural networks using zero-cost proxies, which directly predict the network's performance and avoid the resource-intensive training process. In this paper, we observe that existing zero-cost proxies prefer to high complexity (i.e., Param, FLOPs) networks that are challenging to optimize, which decreases the performance of training-free NAS. Although the skip connection can alleviate the optimization difficulties and reduce the complexity level, it faces significant disadvantages in proxy scoring. Therefore, to address the performance collapse issue, we propose the Manifold Regularization for Training-free NAS (MRT-NAS) that improves the proxy's identification ability of the skip connection structure by measuring the similarity between the network's input and output manifold. Notably, MRT-NAS can be used to regularize any zero-cost proxies in a plug-and-play manner. Experimental results across 3 search spaces and 5 real-world tasks validate the effectiveness of MRT-NAS on boosting the performance of all given zero-cost proxies with negligible time cost. Our implementation is available at https://github.com/yoshimatsuu/MRT-NAS},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
免训练神经架构搜索（NAS）旨在利用零成本代理自动发现高性能神经网络，这些代理直接预测网络的性能并避免资源密集型训练过程。在本文中，我们观察到现有零成本代理偏好高复杂度（即参数、FLOPs）的网络，这些网络难以优化，从而降低了免训练NAS的性能。尽管跳跃连接可以缓解优化困难并降低复杂度水平，但它在代理评分方面面临显著劣势。因此，为了解决性能崩溃问题，我们提出了用于免训练NAS的流形正则化（MRT-NAS），它通过测量网络输入和输出流形之间的相似性来提高代理对跳跃连接结构的识别能力。值得注意的是，MRT-NAS可以以即插即用的方式对任何零成本代理进行正则化。在3个搜索空间和5个真实世界任务上的实验结果验证了MRT-NAS在以可忽略的时间成本提升所有给定零成本代理性能方面的有效性。我们的实现可在https://github.com/yoshimatsuu/MRT-NAS获取。
4463.
Olouladé, Babatoundé Moctard; Gao, Jianliang; Al-Sabri, Raeed; Chen, Jiamin; Wu, Zhenpeng
迈向更好的图异常检测：一种性能感知的神经架构搜索方法 会议文章
收录于: Senn, Walter; Sanguineti, Marcello; Saudargiene, Ausra; Tetko, Igor V.; Villa, Alessandro E. P.; Jirsa, Viktor; Bengio, Yoshua (编辑): Artificial Neural Networks and Machine Learning – ICANN 2025, pp. 285–297, Springer Nature Switzerland, Cham, 2026, ISBN: 978-3-032-04558-4。
@inproceedings{10.1007/978-3-032-04558-4_23,
title = {Towards Better Graph Anomaly Detection: A Performance-Aware Neural Architecture Search Approach},
author = {Babatoundé Moctard Olouladé and Jianliang Gao and Raeed Al-Sabri and Jiamin Chen and Zhenpeng Wu},
editor = {Walter Senn and Marcello Sanguineti and Ausra Saudargiene and Igor V. Tetko and Alessandro E. P. Villa and Viktor Jirsa and Yoshua Bengio},
url = {https://link.springer.com/chapter/10.1007/978-3-032-04558-4_23},
isbn = {978-3-032-04558-4},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2025},
pages = {285–297},
publisher = {Springer Nature Switzerland},
address = {Cham},
abstract = {Detecting anomalies in graph data is a crucial research area with extensive applications across various domains, including but not limited to fraud detection, cybersecurity, health monitoring, and system failure prediction. Graph neural networks (GNNs) have recently gained popularity for anomaly detection tasks due to their powerful capability to leverage complex relationships and inherent structural patterns within graph-based datasets. However, manual design and fine-tuning of GNN architectures are typically time-consuming processes that require considerable expertise. Furthermore, many existing GNN methods predominantly emphasize spatial graph information while neglecting important spectral features, thereby limiting their effectiveness in clearly distinguishing anomalies during information aggregation. To address these issues, we introduce PAGNAS, a Performance-Aware Graph Neural Architecture Search framework specifically tailored for anomaly detection. PAGNAS integrates spectral-based GNN ranking, improving its ability to identify anomalies within graph structures accurately. Our framework leverages a neural performance ranking predictor that automates the selection and optimization of GNN architectures, significantly reducing manual design efforts. By focusing on the discovery of optimal architectures rather than strictly predicting their exact performance, PAGNAS efficiently navigates the architectural search space. Empirical evaluations across four benchmark datasets confirm the effectiveness of PAGNAS. It consistently achieves competitive or superior AUC scores compared to state-of-the-art baselines. These results highlight the robustness of PAGNAS in synthesizing high-performing GNN architectures for anomaly detection in attributed graphs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
在图数据中检测异常是一个重要的研究领域，在各种领域都有广泛的应用，包括但不限于欺诈检测、网络安全、健康监测和系统故障预测。图神经网络（GNNs）由于其强大的能力，能够利用图数据集中的复杂关系和固有结构模式，最近在异常检测任务中受到欢迎。然而，GNN架构的手动设计和微调通常是耗时的过程，需要相当多的专业知识。此外，许多现有的GNN方法主要强调空间图信息，而忽略了重要的谱特征，从而限制了它们在信息聚合过程中清晰区分异常的有效性。为了解决这些问题，我们引入了PAGNAS，一个专门为异常检测量身定制的性能感知图神经架构搜索框架。PAGNAS集成了基于谱的GNN排名，提高了其准确识别图结构中异常的能力。我们的框架利用一个神经性能排名预测器，自动选择和优化GNN架构，显著减少了手动设计工作。PAGNAS通过专注于发现最优架构而不是严格预测其确切性能，高效地导航了架构搜索空间。在四个基准数据集上的实证评估证实了PAGNAS的有效性。与最先进的基线相比，它始终能获得具有竞争力或更优的AUC分数。这些结果突出了PAGNAS在综合用于归因图中异常检测的高性能GNN架构方面的鲁棒性。
4462.
Wang, Xingyu; Ji, Junzhong; Liu, Gan; Xiao, Yadong
PE-RBNAS: 一种采用渐进增强策略的稳健神经架构搜索，用于脑网络分类 期刊文章
收录于: Medical Image Analysis, 卷 107, 页 103813, 2026, ISSN: 1361-8415。
@article{WANG2026103813,
title = {PE-RBNAS: A robust neural architecture search with progressive-enhanced strategies for brain network classification},
author = {Xingyu Wang and Junzhong Ji and Gan Liu and Yadong Xiao},
url = {https://www.sciencedirect.com/science/article/pii/S1361841525003597},
doi = {https://doi.org/10.1016/j.media.2025.103813},
issn = {1361-8415},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Medical Image Analysis},
volume = {107},
pages = {103813},
abstract = {Functional Brain Network (FBN) classification methods based on Neural Architecture Search (NAS) have been increasingly emerging, with their core advantage being the ability to automatically construct high-quality network architectures. However, existing methods exhibit poor robustness when dealing with FBNs that have inherent high-noise characteristics. To address these issues, we propose a robust NAS with progressive-enhanced strategies for FBN classification. Specifically, this method adopts Particle Swarm Optimization as the search method, while treating candidate architectures as individuals, and proposes two progressive-enhanced (PE) strategies to optimize the critical stages of population sampling and fitness evaluation. In the population sampling stage, we first utilize Latin Hypercube Sampling to initialize a small-scale population, ensuring a broad search range. Subsequently, to reduce random fluctuations in searches, we propose a PE supplementary sampling strategy that identifies advantageous regions of the solution space, and performs precise supplementary sampling of the population. In the fitness evaluation stage, to enhance the noise resistance of the searched architectures, we propose a PE fitness evaluation strategy. This strategy first evaluates individual fitness separately using both original data and artificially constructed noise-augmented data, then combines the two fitness scores through a novel progressive formula to determine the final individual fitness. Experiments were conducted on two public datasets: the ABIDE I dataset (1,112 subjects, 17 sites), and ADHD-200 (776 subjects, 8 sites), using AAL/CC200 atlases. Results demonstrate that PE-RBNAS achieves state-of-the-art performance, with 72.61% accuracy on clean ABIDE I data (vs. 71.05% for MC-APSONAS) and 71.82% accuracy under 0.2 noise (vs. 68.15% for PSO-BNAS). The results indicate that, compared to other methods, the proposed method demonstrates better model performance and superior noise resistance.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
基于神经架构搜索（NAS）的功能脑网络（FBN）分类方法不断涌现，其核心优势在于能够自动构建高质量的网络架构。然而，现有方法在处理具有固有高噪声特性的FBN时，鲁棒性较差。为了解决这些问题，我们提出了一种采用渐进增强（PE）策略的稳健NAS，用于FBN分类。具体来说，该方法采用粒子群优化作为搜索方法，将候选架构视为个体，并提出了两种渐进增强（PE）策略来优化种群采样和适应度评估的关键阶段。在种群采样阶段，我们首先利用拉丁超立方体采样初始化小规模种群，确保广泛的搜索范围。随后，为了减少搜索中的随机波动，我们提出了一种PE补充采样策略，该策略识别解空间中的有利区域，并对种群进行精确的补充采样。在适应度评估阶段，为了增强所搜索架构的抗噪声能力，我们提出了一种PE适应度评估策略。该策略首先分别使用原始数据和人工构建的噪声增强数据评估个体适应度，然后通过一种新颖的渐进公式将两个适应度分数结合起来，以确定最终的个体适应度。实验在两个公共数据集上进行：ABIDE I数据集（1,112名受试者，17个站点）和ADHD-200（776名受试者，8个站点），使用AAL/CC200图谱。结果表明，PE-RBNAS在干净的ABIDE I数据上实现了72.61%的准确率（而MC-APSONAS为71.05%），在0.2噪声下实现了71.82%的准确率（而PSO-BNAS为68.15%），达到了最先进的性能。结果表明，与其他方法相比，所提出的方法表现出更好的模型性能和优越的抗噪声能力。
4461.
Xie, Yu; Chang, Yu; Li, Ming; Qin, A. K.; Zhang, Xialei
AutoSGRL: 自动化自监督图表示学习框架构建 期刊文章
收录于: Neural Networks, 卷 194, 页 108119, 2026, ISSN: 0893-6080。
@article{XIE2026108119,
title = {AutoSGRL: Automated framework construction for self-supervised graph representation learning},
author = {Yu Xie and Yu Chang and Ming Li and A. K. Qin and Xialei Zhang},
url = {https://www.sciencedirect.com/science/article/pii/S0893608025009992},
doi = {https://doi.org/10.1016/j.neunet.2025.108119},
issn = {0893-6080},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Neural Networks},
volume = {194},
pages = {108119},
abstract = {Automated machine learning (AutoML) is a promising solution for building a machine learning framework without human assistance and has attracted significant attention throughout the computational intelligence research community. Although there has been an emerging interest in graph neural architecture search, current research focuses on the specific design of semi-supervised or supervised graph neural networks. Motivated by this, we propose a novel method that enables the automatic construction of flexible self-supervised graph representation learning frameworks for the first time as far as we know, referred to as AutoSGRL. Based on existing self-supervised graph contrastive learning methods, AutoSGRL establishes a framework search space for self-supervised graph representation learning, which encompasses data augmentation strategies and proxy tasks for constructing graph contrastive learning frameworks, and the hyperparameters required for model training. Then, we implement an automatic search engine based on genetic algorithms, which constructs multiple self-supervised graph representation learning frameworks as the initial population. By simulating the process of biological evolution including selection, crossover, and mutation, the search engine iteratively evolves the population to identify high-performed frameworks and optimal hyperparameters. Empirical studies demonstrate that our AutoSGRL achieves comparative or even better performance than state-of-the-art manual-designed self-supervised graph representation learning methods and semi-supervised graph neural architecture search methods.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
自动化机器学习 (AutoML) 是一种无需人工协助即可构建机器学习框架的有前景的解决方案，并在计算智能研究社区引起了广泛关注。尽管对图神经网络架构搜索的兴趣日益增长，但目前的研究主要集中在半监督或监督图神经网络的特定设计上。受此启发，我们提出了一种新颖的方法，据我们所知，首次实现了灵活的自监督图表示学习框架的自动构建，称为 AutoSGRL。基于现有的自监督图对比学习方法，AutoSGRL 为自监督图表示学习建立了一个框架搜索空间，该空间包含用于构建图对比学习框架的数据增强策略和代理任务，以及模型训练所需的超参数。然后，我们实现了一个基于遗传算法的自动搜索引擎，它构建了多个自监督图表示学习框架作为初始种群。通过模拟包括选择、交叉和变异在内的生物进化过程，搜索引擎迭代地进化种群以识别高性能框架和最优超参数。实证研究表明，我们的 AutoSGRL 实现了与最先进的手动设计的自监督图表示学习方法和半监督图神经网络架构搜索方法相当甚至更好的性能。
4460.
Xie, Weisheng; Gao, Xiangxiang; Fang, Xuwei; Li, Hui; Hang, Chen; Li, Shaoyuan
收录于: Expert Systems with Applications, 卷 298, 页 129711, 2026, ISSN: 0957-4174。
@article{XIE2026129711,
title = {EQUINAS: Equilibrium-guided differentiable neural architecture search},
author = {Weisheng Xie and Xiangxiang Gao and Xuwei Fang and Hui Li and Chen Hang and Shaoyuan Li},
url = {https://www.sciencedirect.com/science/article/pii/S0957417425033263},
doi = {https://doi.org/10.1016/j.eswa.2025.129711},
issn = {0957-4174},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Expert Systems with Applications},
volume = {298},
pages = {129711},
abstract = {Recent research has significantly mitigated the performance collapse issue in Differentiable Architecture Search (DARTS) by either refining architecture parameters to better reflect the true strengths of operations or developing alternative metrics for evaluating operation significance. However, the actual role and impact of architecture parameters remain insufficiently explored, creating critical ambiguities in the search process. To address this gap, we conduct a rigorous theoretical analysis demonstrating that the change rate of architecture parameters reflects the sensitivity of the supernet’s validation loss in architecture space, thereby influencing the derived architecture’s performance by shaping supernet training dynamics. Building on these insights, we introduce the concept of a Stable Equilibrium State to capture the stability of the bi-level optimization process and propose the Equilibrium Influential (EI) metric to assess operation importance. By integrating these elements, we propose EQUINAS, a differentiable NAS approach that leverages the Stable Equilibrium State to identify the optimal state during the search process and derives the final architecture using the EI metric. Extensive experiments across diverse datasets and search spaces demonstrate that EQUINAS achieves competitive test accuracy compared to state-of-the-art methods while significantly reducing search costs. Additionally, EQUINAS shows remarkable performance in Transformer-based architectures and excels in real-world applications such as image classification and text recognition.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
最近的研究通过改进架构参数以更好地反映操作的真实强度，或开发替代指标来评估操作重要性，显著缓解了可微分架构搜索 (DARTS) 中的性能崩溃问题。然而，架构参数的实际作用和影响尚未充分探索，这在搜索过程中造成了关键的模糊性。为了弥补这一空白，我们进行了严格的理论分析，证明架构参数的变化率反映了超网验证损失在架构空间中的敏感性，从而通过塑造超网训练动态来影响派生架构的性能。基于这些见解，我们引入了稳定平衡态的概念来捕获双层优化过程的稳定性，并提出了平衡影响力 (EI) 指标来评估操作的重要性。通过整合这些元素，我们提出了 EQUINAS，一种可微分的 NAS 方法，它利用稳定平衡态在搜索过程中识别最优状态，并使用 EI 指标派生最终架构。在不同数据集和搜索空间上进行的大量实验表明，EQUINAS 与最先进的方法相比，实现了具有竞争力的测试准确性，同时显著降低了搜索成本。此外，EQUINAS 在基于 Transformer 的架构中表现出色，并在图像分类和文本识别等实际应用中表现卓越。
4459.
Chen, Weiduo; Dong, Xiaoshe; Wang, Qiang
收录于: Future Generation Computer Systems, 卷 175, 页 108071, 2026, ISSN: 0167-739X。
@article{CHEN2026108071,
title = {DP-SWAP: Fast Swapping Strategy Based on Dynamic Programming},
author = {Weiduo Chen and Xiaoshe Dong and Qiang Wang},
url = {https://www.sciencedirect.com/science/article/pii/S0167739X25003656},
doi = {https://doi.org/10.1016/j.future.2025.108071},
issn = {0167-739X},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Future Generation Computer Systems},
volume = {175},
pages = {108071},
abstract = {Neural Architecture Search (NAS) has emerged as an effective approach for automating neural network design. However, NAS imposes significant GPU memory pressure due to the need to evaluate numerous candidate models during training. While tensor swapping helps reduce memory usage, existing tensor selection methods rely on extensive iterative searches, which require repeatedly traversing model computation graphs to evaluate the impact of swapping schemes–leading to high time complexity and poor scalability in dynamic NAS scenarios. To address this issue, we propose DP-SWAP, a novel tensor swapping strategy based on dynamic programming. By leveraging the optimal substructure property of the tensor selection problem, DP-SWAP computes effective swapping schemes with only O(n) time complexity, allows for fast and adaptive decision-making during NAS model exploration. Experimental results show that DP-SWAP achieves training performance comparable to state-of-the-art heuristic methods, while reducing swapping decision time by over 3 orders of magnitude, thus effectively alleviating GPU memory bottlenecks in NAS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
神经架构搜索 (NAS) 已成为一种自动化神经网络设计的有效方法。然而，由于在训练过程中需要评估大量候选模型，NAS 会带来显著的 GPU 内存压力。虽然张量交换有助于减少内存使用，但现有的张量选择方法依赖于大量的迭代搜索，这需要重复遍历模型计算图来评估交换方案的影响——导致时间复杂度高，并且在动态 NAS 场景中可扩展性差。为了解决这个问题，我们提出了 DP-SWAP，一种基于动态规划的新型张量交换策略。通过利用张量选择问题的最优子结构特性，DP-SWAP 仅以 O(n) 的时间复杂度计算有效的交换方案，允许在 NAS 模型探索过程中进行快速自适应决策。实验结果表明，DP-SWAP 实现了与最先进的启发式方法相当的训练性能，同时将交换决策时间缩短了 3 个数量级以上，从而有效缓解了 NAS 中的 GPU 内存瓶颈。
4458.
Li, Jian; Zhu, Yunlong; Dong, Zhicheng; Yang, Hucheng; Cheng, Xudong; Xue, Zhenyu
一种轻量级电弧故障检测模型，集成了多目标架构搜索与动态噪声增强训练 期刊文章
收录于: Measurement, 卷 257, 页 118649, 2026, ISSN: 0263-2241。
@article{LI2026118649,
title = {A lightweight arc fault detection model integrating multi-objective architecture search with dynamic noise-augmented training},
author = {Jian Li and Yunlong Zhu and Zhicheng Dong and Hucheng Yang and Xudong Cheng and Zhenyu Xue},
url = {https://www.sciencedirect.com/science/article/pii/S0263224125020081},
doi = {https://doi.org/10.1016/j.measurement.2025.118649},
issn = {0263-2241},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Measurement},
volume = {257},
pages = {118649},
abstract = {Ensuring accurate and efficient arc fault detection is critical for the safety and reliability of modern electrical systems, particularly in embedded and resource-constrained environments. This paper presents a lightweight convolutional neural network (CNN) model optimized through a multi-objective genetic algorithm (NSGA-II) to achieve a balance between detection accuracy, computational complexity, and noise robustness. The proposed model integrates Squeeze-and-Excitation (SE) attention mechanisms, depthwise separable convolutions, and dynamic Gaussian noise augmentation during training to enhance generalization under noisy conditions. Neural architecture search is employed to automatically design compact yet high-performing architectures, with the final model achieving an F1-score of 99.49 % using only 2529 parameters. The model is validated experimentally on a Raspberry Pi 4B platform, demonstrating an average inference time of 0.785 ms per sample, thereby confirming its real-time detection capability. This study offers a robust, efficient, and practical solution for arc fault diagnosis in embedded industrial applications.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
确保电弧故障检测的准确性和效率对于现代电气系统的安全性和可靠性至关重要，尤其是在嵌入式和资源受限的环境中。本文提出了一种轻量级卷积神经网络（CNN）模型，通过多目标遗传算法（NSGA-II）进行优化，以在检测精度、计算复杂度和噪声鲁棒性之间取得平衡。所提出的模型在训练过程中集成了Squeeze-and-Excitation（SE）注意机制、深度可分离卷积和动态高斯噪声增强，以提高在噪声条件下的泛化能力。采用神经架构搜索自动设计紧凑而高性能的架构，最终模型仅使用2529个参数就达到了99.49%的F1分数。该模型在Raspberry Pi 4B平台上进行了实验验证，平均推断时间为每样本0.785毫秒，从而证实了其实时检测能力。本研究为嵌入式工业应用中的电弧故障诊断提供了一种鲁棒、高效和实用的解决方案。
4457.
Yang, Yeming; Liu, Zhihao; Wong, Ka-Chun; Lin, Qiuzhen; Luo, Jianping; Li, Jianqiang
用于网络入侵检测的进化多任务鲁棒架构搜索 期刊文章
收录于: Expert Systems with Applications, 卷 296, 页 128899, 2026, ISSN: 0957-4174。
@article{YANG2026128899,
title = {Evolutionary multi-task robust architecture search for network intrusion detection},
author = {Yeming Yang and Zhihao Liu and Ka-Chun Wong and Qiuzhen Lin and Jianping Luo and Jianqiang Li},
url = {https://www.sciencedirect.com/science/article/pii/S0957417425025163},
doi = {https://doi.org/10.1016/j.eswa.2025.128899},
issn = {0957-4174},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Expert Systems with Applications},
volume = {296},
pages = {128899},
abstract = {Network Intrusion Detection (NID) becomes a key technology for ensuring network security. Recent researchers have proposed various NID systems based on neural networks. However, these networks require expensive expert knowledge for manual design, which is tedious and time-consuming. Moreover, they easily suffer from adversarial attacks, which limits their application in safety-critical scenarios. To alleviate the above problems, this paper proposes an evolutionary multi-task robust architecture search method, called EMR-NID, which can automatically design robust architectures for NID systems. First, we design an architecture transfer update strategy that achieves information sharing and knowledge transfer between different tasks. Then, we develop an architecture performance correction strategy that enhances the efficiency of robust search and strengthens NID’s defense capability. Finally, our EMR-NID method is validated on three well-known NID datasets, i.e., NSL-KDD, UNSW-NB15, and Edge-IIoTset. The experimental results show that EMR-NID can outperform some state-of-the-art NID methods in terms of clean and robust accuracy under multiple scenarios.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
网络入侵检测 (NID) 已成为确保网络安全的关键技术。最近的研究人员提出了各种基于神经网络的 NID 系统。然而，这些网络需要昂贵的专家知识进行手动设计，这既繁琐又耗时。此外，它们容易受到对抗性攻击，这限制了它们在安全关键场景中的应用。为了缓解上述问题，本文提出了一种进化多任务鲁棒架构搜索方法，称为 EMR-NID，它可以自动设计用于 NID 系统的鲁棒架构。首先，我们设计了一种架构迁移更新策略，实现了不同任务之间的信息共享和知识迁移。然后，我们开发了一种架构性能校正策略，提高了鲁棒搜索的效率并增强了 NID 的防御能力。最后，我们的 EMR-NID 方法在三个著名的 NID 数据集上进行了验证，即 NSL-KDD、UNSW-NB15 和 Edge-IIoTset。实验结果表明，EMR-NID 在多种场景下，在干净和鲁棒准确性方面均优于一些最先进的 NID 方法。
4456.
Poyser, Matt; Breckon, Toby P.
DDS-NAS: 通过在线硬示例挖掘应用于图像分类的神经架构搜索中的动态数据选择 期刊文章
收录于: Pattern Recognition, 卷 169, 页 111948, 2026, ISSN: 0031-3203。
@article{POYSER2026111948,
title = {DDS-NAS: Dynamic data selection within neural architecture search via on-line hard example mining applied to image classification},
author = {Matt Poyser and Toby P. Breckon},
url = {https://www.sciencedirect.com/science/article/pii/S0031320325006089},
doi = {https://doi.org/10.1016/j.patcog.2025.111948},
issn = {0031-3203},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {Pattern Recognition},
volume = {169},
pages = {111948},
abstract = {In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilising an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image within the global dataset in logarithmic time. Via curriculum learning, we then dynamically re-formulate an unbiased subsample dataset for NAS optimisation, upon which the current NAS solution architecture performs poorly. We show that our DDS-NAS framework speeds up gradient-based NAS strategies by up to 27× without loss in performance. By maximising the contribution of each image sample during training, we reduce the duration of a NAS training cycle and the number of iterations required for convergence.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
为了解决神经架构搜索 (NAS) 中的可伸缩性挑战，我们通过课程学习框架中的动态硬示例挖掘来加速 NAS 训练。通过利用强制在潜在空间中进行图像相似性嵌入的自编码器，我们构建了一个高效的 kd 树结构，以低维嵌入中按最远邻居不相似性对图像进行排序。从我们子样本数据集中的给定查询图像，我们可以在对数时间内识别全局数据集中最不相似的图像。通过课程学习，我们然后动态地重新构建一个用于 NAS 优化的无偏子样本数据集，当前 NAS 解决方案架构在该数据集上表现不佳。我们表明，我们的 DDS-NAS 框架将基于梯度的 NAS 策略的速度提高了 27 倍，而性能没有损失。通过最大化训练期间每个图像样本的贡献，我们减少了 NAS 训练周期和收敛所需的迭代次数。
2025
4455.
Wang, Weiqi; Bao, Feilong; Xing, Zhecong; Lian, Zhe
一项调查：特征融合技术的研究进展 期刊文章
收录于: 2025。
@article{wangsurvey,
title = {A Survey: Research Progress of Feature Fusion Technology},
author = {Weiqi Wang and Feilong Bao and Zhecong Xing and Zhe Lian},
url = {http://poster-openaccess.com/files/ICIC2024/862.pdf},
year = {2025},
date = {2025-12-01},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4454.
(编者)
2025.
@collection{nokey,
title = { MACHINE-GENERATED NEURAL NETWORKS FOR SHORT-TERM LOAD FORECASTING},
author = {Gergana Vacheva and Plamen Stanchev and Nikolay Hinov
},
url = {https://unitechsp.tugab.bg/images/2024/1-EE/s1_p143_v1.pdf},
year = {2025},
date = {2025-12-01},
urldate = {2025-12-01},
booktitle = {International Scientific Conference UNITECH`2024},
journal = {International Scientific Conference UNITECH`2024},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4453.
Avval, Sasan Salmani Pour; Abadie, Titouan; Yaghoubi, Vahid
用于工业数据集的神经网络自动化生成，在激光粉末床熔融中的应用 期刊文章
收录于: Journal of Intelligent Manufacturing , 2025。
@article{nokey,
title = {Automated neural network generation for industrial datasets, application to laser powder bed fusion},
author = {
Sasan Salmani Pour Avval and Titouan Abadie and Vahid Yaghoubi
},
url = {https://link.springer.com/article/10.1007/s10845-025-02707-0},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
journal = { Journal of Intelligent Manufacturing },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4452.
(编者)
使用梯度解释器解释 NAS 优化 Transformer 模型用于剩余使用寿命预测 论文集
2025.
@collection{nokey,
title = {Interpreting NAS-Optimized Transformer Models for Remaining Useful Life Prediction Using Gradient Explainer},
author = {Messaouda Nekkaa and Mohamed Abdouni and Dalila Boughaci},
url = {https://annals-csis.org/Volume_44/drp/pdf/8176.pdf},
year = {2025},
date = {2025-11-01},
booktitle = {20th Conference on Computer Science and Intelligence Systems},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4451.
Wang, Yu
机器学习中的架构优化和数据高效方法 博士论文
2025.
@phdthesis{nokey,
title = {Architecture Optimization and Data-Efficient Methods in Machine Learning},
author = {Wang, Yu},
url = {https://escholarship.org/content/qt4rh0v7fg/qt4rh0v7fg.pdf},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
4450.
Balmain, Nate; Jiao, Lei; Li, Jun
2025.
@misc{nokey,
title = {Efficient IoT Anomaly Detection via Graph-Based Neural Architecture Search},
author = {Nate Balmain and Lei Jiao and Jun Li},
url = {https://ljiao.github.io/papers/vcc25.pdf},
year = {2025},
date = {2025-11-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4449.
Liu, Ziti; Liu, Yang; Yan, Xunshi; Liu, Wen; Nie, Han; Guo, Shuaiqi; Zhang, Chen-an
收录于: nature communications, 2025。
@article{nokey,
title = {Automatic network structure discovery of physics informed neural networks via knowledge distillation},
author = {
Ziti Liu and Yang Liu and Xunshi Yan and Wen Liu and Han Nie and Shuaiqi Guo and Chen-an Zhang
},
url = {https://www.nature.com/articles/s41467-025-64624-3},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
journal = {nature communications},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4448.
Liu, Wenbin; Li, Juanjuan; Zeng, Yiliang; Meng, Na; Zhao, Jiahong
一种基于NAS和Transformer的双通道高光谱分类方法 期刊文章
收录于: scientific reports , 2025。
@article{liu-sr25a,
title = {A dual-channel hyperspectral classification method based on NAS and transformer},
author = {
Wenbin Liu and Juanjuan Li and Yiliang Zeng and Na Meng and Jiahong Zhao
},
url = {https://www.nature.com/articles/s41598-025-21399-3},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
journal = { scientific reports },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4447.
Huanga, Kai; Maoa, Yingchi; Zhanga, Benteng; Chena, Yihan; Chena, Yuchu; Wu, Jie
2025.
@misc{Huanga-25a,
title = {Efficient Zero-Cost Neural Architecture Search for Personalized AI Systems in Cloud-Edge Networks},
author = {Kai Huanga and Yingchi Maoa and Benteng Zhanga and Yihan Chena and Yuchu Chena and Jie Wu},
url = {https://cis.temple.edu/~jiewu/research/publications/Publication_files/MASS2025_Efficient%20Zero-Cost%20Neural%20Architecture%20Search%20for%20Personalized%20AI%20Systems%20in%20Cl....pdf},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
keywords = {},
pubstate = {published},
tppubtype = {misc}
}
4446.
Muthusamy, Sudhakar; Ramu, Swarna Priya
一种神经网络架构搜索优化的轻量级注意力集成模型，用于不同作物叶片的养分缺乏和严重性评估 期刊文章
收录于: scientific reports , 2025。
@article{Muthusamy-sr25a,
title = {A neural architecture search optimized lightweight attention ensemble model for nutrient deficiency and severity assessment in diverse crop leaves},
author = {
Sudhakar Muthusamy and Swarna Priya Ramu
},
url = {https://www.nature.com/articles/s41598-025-20124-4},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
journal = {scientific reports },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4445.
Fu, Wenjie; Cui, Wei; Zhang, Shuai; Li, Zhipeng; Chen, Lei; Li, Peng
带掩码预测器的演化图神经网络架构搜索用于配电网络故障检测 期刊文章
收录于: Intelligent Computing, 卷 0, 期 ja, 2025。
@article{<LineBreak>doi:10.34133/icomputing.0229,
title = {Evolutionary Graph Neural Architecture Search with Mask Predictor for Power Distribution Network Fault Detection},
author = {Wenjie Fu and Wei Cui and Shuai Zhang and Zhipeng Li and Lei Chen and Peng Li},
url = {https://spj.science.org/doi/abs/10.34133/icomputing.0229},
doi = {10.34133/icomputing.0229},
year = {2025},
date = {2025-11-01},
journal = {Intelligent Computing},
volume = {0},
number = {ja},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4444.
(编者)
透明视觉：分层不变表示理论 论文集
2025.
@collection{nokey,
title = {Transparent Vision: A Theory of Hierarchical Invariant Representations},
author = {Shuren Qi and Yushu Zhang and Chao Wang and Zhihua Xia and Xiaochun Cao and Fenglei Fan},
url = {https://openaccess.thecvf.com/content/ICCV2025/papers/Qi_Transparent_Vision_A_Theory_of_Hierarchical_Invariant_Representations_ICCV_2025_paper.pdf},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
booktitle = {ICCV 2025},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4443.
(编者)
超越极限：克服基于激活的免训练 NAS 的负相关问题 论文集
2025.
@collection{nokey,
title = {Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS},
author = {Haidong Kang and Lianbo Ma and Pengjun Chen and Guo Yu and Xingwei Wang and Min Huang},
url = {https://openaccess.thecvf.com/content/ICCV2025/papers/Kang_Beyond_the_Limits_Overcoming_Negative_Correlation_of_Activation-Based_Training-Free_NAS_ICCV_2025_paper.pdf},
year = {2025},
date = {2025-11-01},
booktitle = {ICCV 25},
journal = {ICCV 25},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4442.
(编者)
由局部引导扩散驱动的神经网络架构搜索用于个性化联邦学习 论文集
2025.
@collection{Liao-iccv25a,
title = {Neural Architecture Search Driven by Locally Guided Diffusion for Personalized Federated Learning},
author = {Peng Liao and Xilu Wang and Yaochu Jin and Wenli Du and Han Hu},
url = {https://openaccess.thecvf.com/content/ICCV2025/papers/Liao_Neural_Architecture_Search_Driven_by_Locally_Guided_Diffusion_for_Personalized_ICCV_2025_paper.pdf},
year = {2025},
date = {2025-11-01},
urldate = {2025-11-01},
booktitle = {ICCV 25},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4441.
(编者)
2025.
@collection{Yang-iccv25a,
title = {TRNAS: A Training-Free Robust Neural Architecture Search},
author = {Yeming Yang and Qingling Zhu and Jianping Luo and Ka-Chun Wong and Qiuzhen Lin and Jianqiang Li},
url = {https://openaccess.thecvf.com/content/ICCV2025/papers/Yang_TRNAS_A_Training-Free_Robust_Neural_Architecture_Search_ICCV_2025_paper.pdf},
year = {2025},
date = {2025-11-01},
booktitle = {ICCV 2025},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
4440.
Ankalaki, Shilpa
在 AutoML 系统中利用神经网络架构搜索对光谱反射数据进行废水特征参数自动定量 期刊文章
收录于: scientific reports , 2025。
@article{Ankalaki-sr25a,
title = {Automating wastewater characteristic parameter quantitation using neural architecture search in AutoML systems on spectral reflectance data},
author = { Shilpa Ankalaki },
url = {https://www.nature.com/articles/s41598-025-21069-4},
year = {2025},
date = {2025-10-02},
urldate = {2025-10-02},
journal = {scientific reports },
keywords = {},
pubstate = {published},
tppubtype = {article}
}
4439.
Ahmad, Afzal
寻找效率：硬件感知神经网络和高性能 FPGA 加速器的自动化搜索 博士论文
2025.
@phdthesis{Ahmad-phd25a,
title = {Searching for Efficiency: Automated Search for Hardware-Aware Neural Networks and High-Performance FPGA Accelerators},
author = {Afzal Ahmad},
url = {https://www.proquest.com/docview/3261504506?pq-origsite=gscholar&fromopenview=true&sourcetype=Dissertations%20&%20Theses},
year = {2025},
date = {2025-10-02},
urldate = {2025-10-02},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}