神经架构搜索研究进展与未来展望

Research progress and future prospects of neural architecture search

摘要

针对人工设计神经网络架构效率低、寻优困难等问题，梳理了神经架构搜索（NAS）领域近几年的研究进展，不同于传统综述逐一分析 NAS 核心组件的方式，该文基于 2017 年以来的 NAS 文献，构建了一个包含 “核心方法−多目标优化−跨领域协同” 的三维综述框架。通过分析，归纳出 NAS 基于强化学习、进化算法、梯度优化、零成本代理以及单次训练的 5 种核心方法，分析了这些方法对应的多目标优化策略，同时从硬件架构与领域知识融合两个层面探讨了跨领域协同机制。利用该三维分析框架，阐述了 NAS 技术的演进规律，指出了 NAS 在核心方法、多目标优化、跨领域协同方面面临的技术挑战和未来研究方向，为解决现有方法的问题提供了参考，有助于 NAS 技术的进一步发展。

Abstract

To address the challenges of low efficiency and difficulty in optimizing manually designed neural network architectures, this paper reviews the research progress in neural architecture search (NAS) in recent years. Different from traditional reviews that often analyze NAS components individually, this paper builds a three-dimensional review framework based on NAS literature published since 2017, which includes core methods, multi-objective optimization, and cross-domain collaboration. Through analysis, five core NAS methods are identified: Reinforcement learning, evolutionary algorithms, gradient-based optimization, zero-cost proxies, and one-shot training. The corresponding multi-objective optimization strategies for these methods are analyzed, and cross-domain collaboration mechanisms are discussed from two aspects: hardware architecture integration and domain-specific knowledge fusion. Using this three-dimensional analysis framework, the paper describes the evolutionary patterns of NAS technologies, identifies technical challenges and future research directions in core NAS methods, multi-objective optimization, and cross-domain collaboration, and provides references for solving the problems of existing approaches. This contributes to the further development of NAS technologies.

关键词

神经架构搜索 / 自动化机器学习 / 深度学习 / 架构优化 / 多目标优化 / 跨领域协同

Key words

neural architecture search / automated machine learning / deep learning / architecture optimization / multi-objective optimization / cross-domain collaboration

参考文献

[1] KRIZHEVSKY A , SUTSKEVER I , HINTON G E . Imagenet classification with deep convolutional neural networks[C]// Proceedings of the Annual Conference on Neural Information Processing Systems. Red Hook: Curran Associates, Inc., 2012: 1097-1105.

[2] HE K M , ZHANG X Y , REN S Q , et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.

[3] HUANG G , LIU Z , VAN DER MAATEN L , et al. Densely connected convolutional networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2261-2269.

[4] SZEGEDY C , IOFFE S , VANHOUCKE V , et al. Inception—v4, inception—ResNet and the impact of residual connections on learning[C]// 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI Press, 2017: 4278-4284.

[5] VOULODIMOS A , DOULAMIS N , DOULAMIS A , et al. Deep learning for computer vision: A brief review[J]. Computational Intelligence and Neuroscience, 2018, 2018(1): 7068349.

[6] BAHNANAU D , CHO K , BENGIO Y . Neural machine translation by jointly learning to align and translate[EB/OL]. (2016—05—19)[2025—02—17]. https://doi.org/10.48550/arXiv.1409.0473.

[7] VASWANI A , SHAZEER N , PARMAR N , et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 6000-6010.

[8] PRAFUL B J . A comprehensive survey of deep learning techniques natural language processing[J]. European Journal of Technology, 2023, 7(1): 58-66.

[9] KHURANA D , KOLI A , KHATTER K , et al. Natural language processing: State of the art, current trends and challenges[J]. Multimedia Tools and Applications, 2023, 82(3): 3713-3744.

[10] COVINGTON P , ADAMS J , SARGIN E . Deep neural networks for YouTube recommendations[C]// Proceedings of the 10th ACM Conference on Recommender Systems. New York: ACM, 2016: 191-198.

[11] WANG J Z , HUANG P P , ZHAO H , et al. Billion—scale commodity embedding for e—commerce recommendation in alibaba[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York: ACM, 2018: 839-848.

[12] RADFORD A , NARASIMHAN K , SALIMANS T , et al. Improving language understanding by generative pre—training[EB/OL]. (2018—06—11)[2025—02—17]. https://www.mikecaptain.com/resources/pdf/GPT—1.pdf.

[13] RAIAAN M A K , MUKTA M S H , FATEMA K , et al. A review on large language models: Architectures, applications, taxonomies, open issues and challenges[J]. IEEE Access, 2024, 12: 26839-26874.

[14] BROWN T , MANN B , RYDER N , et al. Language models are few—shot learners[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. New York: ACM, 2020: 1877-1901.

[15] HANNUN A , CASE C , CASPER J , et al. Deep Speech: Scaling up end—to—end speech recognition[EB/OL]. (2014—12—19)[2025—02—17]. https://doi.org/10.48550/arXiv.1412.5567.

[16] CHOROWSKI J K , BAHNANAU D , SERDYUK D , et al. Attention—based models for speech recognition[C]// Proceedings of the 29th International Conference on Neural Information Processing Systems. New York: ACM, 2015: 577-585.

[17] CHAN W , JAITLY N , LE Q , et al. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition[C]// Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2016: 4960-4964.

[18] HOCHREITER S , SCHMIDHUBER J . Long short—term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

[19] CHEN M X , FIRAT O , BAPNA A , et al. The best of both worlds: Combining recent advances in neural machine translation[EB/OL]. (2018—04—27)[2025—02—17]. https://doi.org/10.48550/arXiv.1804.09849.

[20] WU Y , SCHUSTER M , CHEN Z , et al. Google’s neural machine translation system: Bridging the gap between human and machine translation[EB/OL]. (2016—10—08)[2025—02—17]. https://doi.org/10.48550/arXiv.1609.08144.

[21] SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large—scale image recognition[C]// International Conference on Learning Representations. San Diego: Computational and Biological Learning Society, 2015: 1-14.

[22] HOWARD A G , ZHU M , CHEN B , et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[EB/OL]. (2017—04—17)[2025—02—17]. https://doi.org/10.48550/arXiv.1704.04861.

[23] KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks[C]// Proceedings of the Communications of the ACM. New York: ACM, 2017: 84-90.

[24] REN S Q , HE K M , GIRSHICK R , et al. Faster R—CNN: Towards real—time object detection with region proposal networks[C]// Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Piscataway: IEEE, 2017: 1137-1149.

[25] LIU W , ANGUELOV D , ERHAN D , et al. SSD: Single shot multibox detector[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2016: 21-37.

[26] LIN T Y , GOYAL P , GIRSHICK R , et al. Focal loss for dense object detection[C]// Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2980-2988.

[27] ZOPH B , VASUDEVAN V , SHLENS J , et al. Learning transferable architectures for scalable image recognition[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8697-8710.

[28] ELSKEN T , METZEN J H , HUTTER F . Neural architecture search: A survey[J]. Journal of Machine Learning Research, 2019, 20(55): 1-21.

[29] CAI H , GAN C , WANG T , et al. Once for all: Train one network and specialize it for efficient deployment[EB/OL]. (2020—04—29)[2025—02—17]. https://doi.org/10.48550/arxiv.1908.09791.

[30] ZOPH B , LE Q . Neural architecture search with reinforcement learning[EB/OL]. (2017—02—15)[2025—02—17]. https://doi.org/10.48550/arXiv.1611.01578.

[31] PHAM H , GUAN M Y , ZOPH B , et al. Efficient neural architecture search via parameter sharing[C]// International Conference on Machine Learning. Stockholm: PMLR, 2018: 4095-4104.

[32] DENG D , LINDAUER M . Literature list on neural architecture search[EB/OL]. [ 2025—02—17]. https://www.automl.org/automl/literature—on—neural—architecture—search/.

[33] WISTUBA M , RAWAT A , PEDAPATI T . A survey on neural architecture search[EB/OL]. (2019—06—18)[2025—02—17]. https://doi.org/10.48550/arXiv.1905.01392.

[34] JAAFRA Y , LAURENT J L , DERUYVER A , et al. Reinforcement learning for neural architecture search: A review[J]. Image and Vision Computing, 2019, 89: 57-66.

[35] HU Y Q , YU Y . A technical view on neural architecture search[J]. International Journal of Machine Learning and Cybernetics, 2020, 11(4): 795-811.

[36] POORNACHANDRA S , PRAPULLA S . Neural architecture search in classical and quantum computers: A survey[J]. International Research Journal of Engineering and Technology, 2020, 7(6): 1-6.

[37] 耿飞, 王春楠, 王宏志 . 神经网络架构搜索综述[J]. 智能计算机与应用, 2020, 10(6): 25-30.

[38] GENG F , WANG C N , WANG H Z . Neural architecture search: A survey[J]. Intelligent Computer and Applications, 2020, 10(6): 25-30.

[39] 葛道辉, 李洪升, 张亮, 等 . 轻量级神经网络架构综述[J]. 软件学报, 2020, 31(9): 2627-2653.

[40] GE D H , LI H S , ZHANG L , et al. Survey of lightweight neural network[J]. Journal of Software, 2020, 31(9): 2627-2653.

[41] YU T , WANG C , ZHANG X F , et al. A review of neural architecture search[M]//WANG Y, MARTINSEN K, YU T , et al. Advanced Manufacturing and Automation XI. Singapore: Springer, 2022: 648-652.

[42] LIU Y , SUN Y , XUE B , et al. A survey on evolutionary neural architecture search[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34(2): 550-570.

[43] GANEPOLA V V V , WIRASINGHA T . Automating generative adversarial networks using neural architecture search: A review[C]// Proceedings of the International Conference on Emerging Smart Computing and Informatics. Piscataway: IEEE, 2021: 577-582.

[44] ZHU H , ZHANG H , JIN Y . From federated learning to federated neural architecture search: A survey[J]. Complex & Intelligent Systems, 2021, 7(2): 639-657.

[45] SANTRA S , HSIEH J W , LIN C F . Gradient descent effects on differential neural architecture search: A survey[J]. IEEE Access, 2021, 9: 89602-89618.

[46] OLOULADE B M , GAO J L , CHEN J M , et al. Graph neural architecture search: A survey[J]. Tsinghua Science and Technology, 2021, 27(4): 692-708.

[47] BUTHGAMUMUDALIGE V U , WIRASINGHA T . Neural architecture search for generative adversarial networks: A review[C]// Proceedings of the 10th International Conference on Information and Automation for Sustainability. Piscataway: IEEE, 2021: 246-251.

[48] REN P , XIAO Y , CHANG X , et al. A comprehensive survey of neural architecture search: Challenges and solutions[J]. ACM Computing Surveys, 2021, 54(4): 1-34.

[49] 孟子尧, 谷雪, 梁艳春, 等 . 深度神经架构搜索综述[J]. 计算机研究与发展, 2021, 58(1): 22-33.

[50] MENG Z Y , GU X , LIANG Y C , et al. Deep neural architecture search: A survey[J]. Journal of Computer Research and Development, 2021, 58(1): 22-33.

[51] BAYMURZINA D , GOLIKOV E , BURTSEV M . A review of neural architecture search[J]. Neurocomputing, 2022, 474: 82-93.

[52] LIU S Q , ZHANG H Y , JIN Y C . A survey on computationally efficient neural architecture search[J]. Journal of Automation and Intelligence, 2022, 1(1): 100002.

[53] CHITTY—VENKATA K T , EMANI M , VISHWANATH V , et al. Neural architecture search for transformers: A survey[J]. IEEE Access, 2022, 10: 108374-108412.

[54] WHITE C , SAFARI M , SUKTHANKER R , et al. Neural architecture search: Insights from 1000 papers[EB/OL]. (2023—01—25)[2025—02—17]. https://doi.org/10.48550/arXiv.2301.08727.

[55] SONG X , XIE X , LYU Z , et al. Efficient evaluation methods for neural architecture search: A survey[EB/OL]. (2024—10—09)[2025—02—17]. https://doi.org/10.48550/arXiv.2301.05919.

[56] 丁丁, 刘文哲, 盛常冲, 等 . 神经网络架构搜索研究进展与展望[J]. 国防科技大学学报, 2023, 45(6): 100-131.

[57] DING D , LIU W Z , SHENG C C , et al. State of the art and prospects of neural architecture search[J]. Journal of National University of Defense Technology, 2023, 45(6): 100-131.

[58] 薛羽, 张逸轩 . 深层神经网络架构搜索综述[J]. 信息网络安全, 2023, 23(9): 58-74.

[59] XUE Y , ZHANG Y X . Survey on deep neural architecture search[J]. Netinfo Security, 2023, 23(9): 58-74.

[60] WU M T , TSAI C W . Training—free neural architecture search: A review[J]. ICT Express, 2024, 10(1): 213-231.

[61] 孙仁科, 皇甫志宇, 陈虎, 等 . 神经架构搜索综述[J]. 计算机应用, 2024, 44(10): 2983-2994.

[62] SUN R K , HUANGFU Z Y , CHEN H , et al. Survey of neural architecture search[J]. Journal of Computer Applications, 2024, 44(10): 2983-2994.

[63] ZHANG X , JIANG W , SHI Y , et al. When neural architecture search meets hardware implementation: From hardware awareness to co—design[C]// Proceedings of the IEEE Computer Society Annual Symposium on VLSI. Los Alamitos: IEEE, 2019: 25-30.

[64] BENMEZIANE H , MAGHRAOUI K E , OUARNOUGHI H , et al. A comprehensive survey on hardware—aware neural architecture search[EB/OL]. (2021—01—22)[2025—02—17]. https://doi.org/10.48550/arXiv.2101.09336.

[65] BENMEZIANE H , EL MAGHRAOUI K , OUARNOUGHI H , et al. Hardware—aware neural architecture search: Survey and taxonomy[C]// Proceedings of the 30th International Joint Conference on Artificial Intelligence. Montreal: IJCAI Organization, 2021: 4322-4329.

[66] SEKANINA L . Neural architecture search and hardware accelerator co—search: A survey[J]. IEEE Access, 2021, 9: 151337-151362.

[67] CHITTY—VENKATA K T , SOMANI A K . Neural architecture search survey: A hardware perspective[J]. ACM Computing Surveys, 2022, 55(4): 1-36.

[68] CHITTY—VENKATA K T , EMANI M , VISHWANATH V , et al. Neural architecture search benchmarks: Insights and survey[J]. IEEE Access, 2023, 11: 25217-25236.

[69] BAKER B , GUPTA O , NAIK N , et al. Designing neural network architectures using reinforcement learning[EB/OL]. (2017—03—22)[2025—02—17]. https://doi.org/10.48550/arXiv.1611.02167.

[70] LIU H , SIMONYAN K , YANG Y . DARTS: Differentiable architecture search[C]// Proceedings of the 7th International Conference on Learning Representations. New Orleans: [s.n.], 2019: 1-13.

[71] REAL E , LIANG C , SO D , et al. AutoML—Zero: Evolving machine learning algorithms from scratch[C]// Proceedings of the 37th International Conference on Machine Learning. [S.l.]: PMLR, 2020: 8007-8019.

[72] CAI H , GAN C , WANG T Z , et al. Once—for—all: Train one network and specialize it for efficient deployment[EB/OL]. (2020—04—29)[2025—02—17]. https://doi.org/10.48550/arXiv.1908.09791.

[73] LIU S W , MOCANU D C , MATAVALAM A R R , et al. Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware[J]. Neural Computing and Applications, 2021, 33: 2589-2604.

[74] QIN Y , ZHANG Z , WANG X , et al. NAS—bench—graph: Benchmarking graph neural architecture search[C]// Proceedings of the Advances in Neural Information Processing Systems. Red Hook: Curran Associates, Inc., 2022: 54-69.

[75] MILLS K G , NIU D , SALAMEH M , et al. AIO—P: Expanding neural performance predictors beyond image classification[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2023, 37(8): 9180-9189.

[76] MITTAL D , LEE W S . Differentiable tree search in latent state space[EB/OL]. (2024—05—03)[2025—02—16]. https://openreview.net/pdf?id=IjJU2BRSCV.

[77] HSU C H , CHANG S H , LIANG J H , et al. MONAS: Multi—objective neural architecture search using reinforcement learning[EB/OL]. (2018—12—03)[2025—02—17]. https://doi.org/10.48550/arXiv.1806.10332.

[78] TIAN Y , WANG Q , HUANG Z W , et al. Off—policy reinforcement learning for efficient and effective GAN architecture search[C]// European Conference on Computer Vision. Cham: Springer, 2020: 175-192.

[79] GAO Y , YANG H , ZHANG P , et al. Graph neural architecture search[C]// Proceedings of the 29th International Joint Conference on Artificial Intelligence. [S.l.]: International Joint Conferences on Artificial Intelligence Organization, 2020: 1403-1409.

[80] REAL E , AGGARWAL A , HUANG Y P , et al. Regularized evolution for image classifier architecture search[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 4780-4789.

[81] MÄRTENS M , IZZO D . Neural network architecture search with differentiable Cartesian genetic programming for regression[C]// Proceedings of the Genetic and Evolutionary Computation Conference Companion. New York: ACM, 2019: 181-182.

[82] CHEN Y M , PAN T C , HE C , et al. Efficient evolutionary deep neural architecture search (NAS) by noisy network morphism mutation[C]// International Conference on Bio—Inspired Computing: Theories and Applications. Singapore: Springer, 2019: 497-508.

[83] ELSKEN T, METZEN J H, HUTTER F. Efficient multi—objective neural architecture search via Lamarckian evolution[EB/OL]. (2019—02—26)[2025—02—17]. https://doi.org/10.48550/arXiv.1804.09081.

[84] ZHOU D Z , ZHOU X C , ZHANG W W , et al. EcoNAS: Finding proxies for economical neural architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11396-11404.

[85] CHEN L , XU H . Mfenas: Multifactorial evolution for neural architecture search[C]// Proceedings of the Genetic and Evolutionary Computation Conference Companion. New York: ACM, 2022: 631-634.

[86] O'NEILL D , XUE B , ZHANG M J . Evolutionary neural architecture search for high—dimensional skip—connection structures on DenseNet style networks[J]. IEEE Transactions on Evolutionary Computation, 2021, 25(6): 1118-1132.

[87] SHI M , TANG Y F , ZHU X Q , et al. Genetic—GNN: Evolutionary architecture search for graph neural networks[J]. Knowledge—Based Systems, 2022, 247: 108752.

[88] KOBAYASHI M , NAGAO T . A Multi—objective architecture search for generative adversarial networks[C]// Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion. New York: ACM, 2020: 133-134.

[89] SHI H , PI R , XU H , et al. Bridging the gap between sample—based and one—shot neural architecture search with BONAS[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. New York: ACM, 2020: 1808-1819.

[90] PENG Y M , SONG A , CIESIELSKI V , et al. PRE—NAS: Predictor—assisted evolutionary neural architecture search[C]// Proceedings of the Genetic and Evolutionary Computation Conference. New York: ACM, 2022: 1066-1074.

[91] WEI C , NIU C , TANG Y P , et al. NPENAS: Neural predictor guided evolution for neural architecture search[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 34(11): 8441-8455.

[92] YANG Z H , WANG Y H , CHEN X H , et al. CARS: Continuous evolution for efficient neural architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1829-1838.

[93] LIANG J , MEYERSON E , MIIKKULAINEN R . Evolutionary architecture search for deep multitask networks[C]// Proceedings of the Genetic and Evolutionary Computation Conference. New York: ACM, 2018: 466-473.

[94] LIU H X , SIMONYAN K , VINYALS O , et al. Hierarchical representations for efficient architecture search[EB/OL]. (2018—02—22)[2025—02—17]. https://doi.org/10.48550/arXiv.1711.00436.

[95] VAN WYK G J , BOSMAN A S . Evolutionary neural architecture search for image restoration[C]// Proceedings of the International Joint Conference on Neural Networks. Piscataway: IEEE, 2019: 1-8.

[96] JOHNER F M , WASSNER J . Efficient evolutionary architecture search for CNN optimization on GTSRB[C]// Proceedings of the 18th IEEE International Conference on Machine Learning and Applications. Piscataway: IEEE, 2019: 56-61.

[97] WEN Y W , PENG S H , TING C K . Two—stage evolutionary neural architecture search for unsupervised anomaly detection in sensor networks[C]// 2020 15th International Symposium on Autonomous and Intelligent Systems (ISIS). Piscataway: IEEE, 2020: 47-52.

[98] ZHU H Y , JIN Y C . Real—time federated evolutionary neural architecture search[J]. IEEE Transactions on Evolutionary Computation, 2021, 26(2): 364-378.

[99] HO K , GILBERT A , JIN H L , et al. Neural architecture search for deep image prior[J]. Computers & Graphics, 2021, 98: 188-196.

[100] KYRIAKIDES G , MARGARITIS K . Evolving graph convolutional networks for neural architecture search[J]. Neural Computing and Applications, 2022, 34(2): 899-909.

[101] 王龙业, 肖舒, 曾晓莉, 等 . 基于代理模型进化的高效神经网络架构搜索[J]. 计算机仿真, 2024, 41(5): 359-365.

[102] WANG L Y , XIAO S , ZENG X L , et al. Efficient neural architecture search based on surrogate model evolution[J]. Computer Simulation, 2024, 41(5): 359-365.

[103] PRECHELT L . Early stopping—but when?[M]//MONTAVON G, ORR G B, MÜLLER K R. Neural Networks: Tricks of the Tracle. Berlin: Springer, 2002: 55-69.

[104] DEB K , PRATAP A , AGARWAL S , et al. A fast and elitist multiobjective genetic algorithm: NSGA—II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.

[105] ZHANG Q F , LI H . MOEA/D: A multiobjective evolutionary algorithm based on decomposition[J]. IEEE Transactions on Evolutionary Computation, 2007, 11(6): 712-731.

[106] XIE S , ZHENG H , LIU C , et al. SNAS: Stochastic neural architecture search[EB/OL]. (2020—04—01)[2025—02—17]. https://doi.org/10.48550/arXiv.1812.09926.

[107] HE C Y , YE H S , SHEN L , et al. MileNAS: Efficient neural architecture search via mixed—level reformulation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11993-12002.

[108] HONG S G , KIM D H , CHOI M K . Memory—efficient models for scene text recognition via neural architecture search[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops. Piscataway: IEEE, 2020: 183-191.

[109] WAN A , DAI X L , ZHANG P Z , et al. FBNetV2: Differentiable neural architecture search for spatial and channel dimensions[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 12965-12974.

[110] GUILIN L , XING Z , ZITONG W , et al. StacNAS: Towards stable and consistent optimization for differentiable neural architecture search[EB/OL]. (2019—09—26)[2025—02—17]. https://openreview.net/pdf?id=rygpAnEKDH.

[111] HOU P F , JIN Y , CHEN Y . Single—DARTS: Towards stable architecture search[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Piscataway: IEEE, 2021: 373-382.

[112] YE P , LI B P , LI Y K , et al. β—DARTS: Beta—decay regularization for differentiable architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 10874-10883.

[113] XUE Y , QIN J F . Partial connection based on channel attention for differentiable neural architecture search[J]. IEEE Transactions on Industrial Informatics, 2022, 19(5): 6804-6813.

[114] LU Z C , DEB K , GOODMAN E , et al. NSGANetV2: Evolutionary multi—objective surrogate—assisted neural architecture search[C]// European Conference on Computer Vision. Cham: Springer, 2020: 35-51.

[115] HE C , MUSHTAQ E , DING J , et al. FedNAS: Federated deep learning via neural architecture search[EB/OL]. (2022—01—28)[2025—02—17]. https://openreview.net/pdf?id=1OHZX4YDqhT.

[116] 杨军, 蔺颖婕, 周鹏 . 基于关系特征的可微图神经架构搜索[EB/OL]. (2025—01—06)[ 2025—02—28]. https://doi.org/10.13700/j.bh.1001—5965.2024.0794.

[117] YANG J , LIN Y J , ZHOU P . Differentiable graph neural architecture search based on relation feature[EB/OL]. (2025—01—06)[ 2025—02—28]. https://doi.org/10.13700/j.bh.1001—5965.2024.0794.

[118] CHO H , SHIN J , RHEE W . B2EA: An evolutionary algorithm assisted by two Bayesian optimization modules for neural architecture search[EB/OL]. [ 2025—02—17]. https://doi.org/10.48550/arXiv.2202.03005.

[119] 薛羽, 卢畅畅 . 基于有偏采样的连续进化神经架构搜索[J]. 计算机工程, 2024, 50(2): 91-97.

[120] XUE Y , LU C C . Continuous evolutionary neural architecture search based on biased sampling[J]. Computer Engineering, 2024, 50(2): 91-97.

[121] 蒋鹏程, 薛羽 . 基于排序得分预测的演化神经架构搜索方法[J]. 计算机学报, 2024, 47(11): 2522-2535.

[122] JIANG P C , XUE Y . Evolutionary neural architecture search with predictor of ranking—based score[J]. Chinese Journal of Computers, 2024, 47(11): 2522-2535.

[123] SHIN R , PACKER C , SONG D . Differentiable neural network architecture search[EB/OL]. (2018—02—13)[2025—02—17]. https://openreview.net/pdf?id=BJ—MRKkwG.

[124] DONG X Y , YANG Y . Searching for a robust neural architecture in four GPU hours[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 1761-1770.

[125] TAN H , CHENG R , HUANG S H , et al. RelativeNAS: Relative neural architecture search via slow—fast learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34(1): 475-489.

[126] ZHANG M , SU S W , PAN S , et al. Idarts: Differentiable architecture search with stochastic implicit gradients[C]// International Conference on Machine Learning. [S.l.]: PMLR, 2021: 12557-12566.

[127] GU Y C , WANG L J , LIU Y , et al. DOTS: Decoupling operation and topology in differentiable architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 12311-12320.

[128] XUE S , WANG R Q , ZHANG B C , et al. IDARTS: Interactive differentiable architecture search[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 1163-1172.

[129] SHU Y , DAI Z , WU Z , et al. Unifying and boosting gradient—based training—free neural architecture search[C]// Proceedings of the Advances in Neural Information Processing Systems. Red Hook: Curran Associates, Inc., 2022: 33001-33015.

[130] YU H Y , PENG H W , HUANG Y , et al. Cyclic differentiable architecture search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1): 211-228.

[131] ZHANG X Y , LI Y G , ZHANG X Y , et al. Differentiable architecture search with random features[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023: 16060-16069.

[132] CHEN X , XIE L X , WU J , et al. Progressive differentiable architecture search: Bridging the depth gap between search and evaluation[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1294-1303.

[133] HUANG S Y , CHU W T . PONAS: Progressive one—shot neural architecture search for very efficient deployment[C]// Proceedings of the International Joint Conference on Neural Networks. Piscataway: IEEE, 2021: 1-9.

[134] WU B C , DAI X L , ZHANG P , et al. FBNet: Hardware—aware efficient convnet design via differentiable neural architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 10734-10742.

[135] MELLOR J , TURNER J , STORKEY A , et al. Neural architecture search without training[C]// Proceedings of the 38th International Conference on Machine Learning. [S.l.]: PMLR, 2021: 7588-7598.

[136] ABDLEFATTAH M S , MEHROTRA A , DUDZIAK Ł , et al. Zero—cost proxies for lightweight NAS[C]// Proceedings of the 9th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2021: 1-21.

[137] ZHANG Z , JIA Z . GradSign: Model performance inference with theoretical insights[C]// Proceedings of the 10th International Conference on Learning Representations. San Diego: [s.n.], 2022: 1-17.

[138] WU M T , LIN H I , TSAI C W . A training—free genetic neural architecture search[C]// Proceedings of the 2021 ACM International Conference on Intelligent Computing and Its Emerging Applications. New York: ACM, 2021: 65-70.

[139] CAVAGNERO N , ROBBIANO L , CAPUTO B , et al. FreeREA: Training—free evolution—based architecture search[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2023: 1493-1502.

[140] ZHOU Q Q , SHENG K K , ZHENG X W , et al. Training—free transformer architecture search with zero—cost proxy guided evolution[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(10): 6525-6541.

[141] ZHANG M , PAN S R , CHANG X J , et al. BaLeNAS: Differentiable architecture search via the Bayesian learning rule[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 11871-11880.

[142] XIANG L C , DUDZIAK L , ABDELFATTAH M S , et al. Zero—cost operation scoring in differentiable architecture search[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2023: 10453-10463.

[143] JAVAHERIPI M , SHAH S , MUKHERJEE S , et al. Litetransformersearch: Training—free on—device search for efficient autoregressive language models[C]// Proceedings of the 1st International Conference on Automated Machine Learning Late—Breaking Workshop. Baltimore: PMLR, 2022.

[144] MOKHTARI N , NÉDÉLEC A , GILLES M , et al. Improving neural architecture search by mixing a firefly algorithm with a training free evaluation[C]// Proceedings of the International Joint Conference on Neural Networks. Piscataway: IEEE, 2022: 1-8.

[145] WHITE C , KHODAK M , TU R , et al. A deeper look at zero—cost proxies for lightweight NAS[EB/OL]. (2022—03—25)[2025—02—16]. https://iclr—blog—track.github.io/2022/03/25/zero—cost—proxies/.

[146] LIN M , WANG P , SUN Z , et al. Zen—nas: A zero—shot nas for high—performance image recognition[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 347-356.

[147] BROCK A , LIM T , RITCHIE J M , et al. SMASH: One—shot model architecture search through hypernetworks[EB/OL]. (2017—08—17)[2025—02—17]. https://doi.org/10.48550/arXiv.1708.05344.

[148] BENDER G , KINDERMANS P J , ZOPH B , et al. Understanding and simplifying one—shot architecture search[C]// Proceedings of the 35th International Conference on Machine Learning. Stockholm: PMLR, 2018: 550-559.

[149] DONG X Y , YANG Y . One—shot neural architecture search via self—evaluated template network[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 3681-3690.

[150] AKIMOTO Y , SHIRAKAWA S , YOSHINARI N , et al. Adaptive stochastic natural gradient method for one—shot neural architecture search[C]// International Conference on Machine Learning. [S.l.]: PMLR, 2019: 171-180.

[151] YOU S , HUANG T , YANG M M , et al. GreedyNAS: Towards fast one—shot NAS with greedy supernet[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 1999-2008.

[152] ZHOU Z X , NING X F , CAI Y , et al. CLOSE: Curriculum learning on the sharing extent towards better one—shot NAS[C]// European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 578-594.

[153] LI X , LIN C , LI C M , et al. Improving one—shot NAS by suppressing the posterior fading[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 13836-13845.

[154] ZHANG M , LI H Q , PAN S R , et al. One—shot neural architecture search: Maximising diversity to overcome catastrophic forgetting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(9): 2921-2935.

[155] ZHANG M Y , YU X Y , ZHAO H D , et al. ShiftNAS: Improving one—shot NAS via probability shift[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 5919-5928.

[156] GUO R H , LIN C , LI C M , et al. Powering one—shot topological NAS with stabilized share—parameter proxy[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 625-641.

[157] XIA X , XIAO X F , WANG X , et al. Progressive automatic design of search space for one—shot neural architecture search[C]// Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2022: 2455-2464.

[158] LIANG T T , WANG Y T , TANG Z , et al. OPANAS: One—shot path aggregation network architecture search for object detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 10195-10203.

[159] YAN B , PENG H W , WU K , et al. LightTrack: Finding lightweight neural networks for object tracking via one—shot architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 15180-15189.

[160] CHEN O T C , ZHANG Y C , CHANG Y X , et al. Iterative multiple—path one—shot NAS for the optimized performance[C]// Proceedings of the IEEE International Symposium on Circuits and Systems. Piscataway: IEEE, 2021: 1-5.

[161] LI Y X , WEN Z A , WANG Y H , et al. One—shot graph neural architecture search with dynamic search space[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Virtual Event: AAAI Press, 2021: 8510-8517.

[162] PENG H , DU H , YU H , et al. Cream of the crop: Distilling prioritized paths for one—shot neural architecture search[J]. Advances in Neural Information Processing Systems, 2020, 33: 17955-17964.

[163] ZHANG X B , HUANG Z H , WANG N Y , et al. You only search once: Single shot neural architecture search via direct sparse optimization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(9): 2891-2904.

[164] GUO Z C , ZHANG X Y , MU H Y , et al. Single path one—shot neural architecture search with uniform sampling[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 544-560.

[165] ZHANG M , LI H , PAN S , et al. Overcoming multi—model forgetting in one—shot NAS with diversity maximization[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 7809-7818.

[166] HUANG S Y , CHU W T . Searching by generating: Flexible and efficient one—shot NAS with architecture generator[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 983-992.

[167] CHEN M H , FU J L , LING H B . One—shot neural ensemble architecture search by diversity—guided search space shrinking[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 16530-16539.

[168] XUE C , WANG X X , YAN J C , et al. Rethinking bi—level optimization in neural architecture search: A Gibbs sampling perspective[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo ALto: AAAI Press, 2021: 10551-10559.

[169] ZHANG M , LI H Q , PAN S R , et al. One—shot neural architecture search via novelty driven sampling[C]// Proceedings of the 29th International Joint Conference on Artificial Intelligence. [S.l.]: International Joint Conferences on Artificial Intelligence Organization, 2020: 3188-3194.

[170] LIANG H W , ZHANG S F , SUN J C , et al. DARTS+: Improved differentiable architecture search with early stopping[EB/OL]. (2020—10—20)[2025—02—17]. https://doi.org/10.48550/arXiv.1909.06035.

[171] YAN S , FANG B Y , ZHANG F E , et al. HM—NAS: Efficient neural architecture search via hierarchical masking[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. Piscataway: IEEE, 2019: 1942-1950.

[172] BENDER G , LIU H X , CHEN B , et al. Can weight sharing outperform random architecture search? An investigation with TuNAS[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 14323-14332.

[173] DONG X , TAN M , YU A W , et al. AutoHAS: Efficient hyperparameter and architecture search[EB/OL]. (2021—04—07)[2025—02—17]. https://doi.org/10.48550/arXiv.2006.03656.

[174] LIU C X , ZOPH B , NEUMANN M , et al. Progressive neural architecture search[C]// Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 19-34.

[175] TAN M X , LE Q V . EfficientNet: Rethinking model scaling for convolutional neural networks[C]// Proceedings of the 36th International Conference on Machine Learning. Long Beach: PMLR, 2019: 6105-6114.

[176] DONG J D , CHENG A C , JUAN D C , et al. DPP—Net: Device—aware progressive search for Pareto—optimal neural architectures[C]// Proceedings of the European Conference on Computer Vision. Cham: Springer, 2018: 517-531.

[177] LU Z , WHALEN I , BODDETI V , et al. NSGA—net: Neural architecture search using multi—objective genetic algorithm[C]// Proceedings of the Genetic and Evolutionary Computation Conference. Prague: ACM, 2019: 419-427.

[178] LI X , ZHOU Y M , PAN Z , et al. Partial order pruning: for best speed/accuracy trade—off in neural architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 9145-9153.

[179] MARCHISIO A , MASSA A , MRAZEK V , et al. NASCaps: A framework for neural architecture search to optimize the accuracy and hardware efficiency of convolutional capsule networks[C]// Proceedings of the 39th International Conference on Computer—Aided Design. New York: ACM, 2020: 1-9.

[180] JIANG J , HAN F , LING Q H , et al. Efficient network architecture search via multiobjective particle swarm optimization based on decomposition[J]. Neural Networks, 2020, 123: 305-316.

[181] LU Z C , SREEKUMAR G , GOODMAN E , et al. Neural architecture transfer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(9): 2971-2989.

[182] CHEN Y K , MENG G F , ZHANG Q , et al. RENAS: Reinforced evolutionary neural architecture search[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 4787-4796.

[183] GONG X Y , CHANG S Y , JIANG Y F , et al. AutoGAN: Neural architecture search for generative adversarial networks[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 3224-3234.

[184] CHU X X , ZHANG B , XU R J . Multi—objective reinforced evolution in mobile neural architecture search[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 99-113.

[185] KWASIGROCH A , GROCHOWSKI M , MIKOŁAJCZYK A . Neural architecture search for skin lesion classification[J]. IEEE Access, 2020, 8: 9061-9071.

[186] ACHARARIT P , HANIF M A , PUTRA R V W , et al. APNAS: Accuracy—and—performance—aware neural architecture search for neural hardware accelerators[J]. IEEE Access, 2020, 8: 165319-165334.

[187] ANDERSON A , SU J , DAHYOT R, et al. Performance—oriented neural architecture search[C]// Proceedings of the International Conference on High Performance Computing & Simulation. Piscataway: IEEE, 2019: 177-184.

[188] JIANG W W , ZHANG X Y , SHA E H M , et al. Accuracy vs. efficiency: Achieving both through FPGA—implementation aware neural architecture search[C]// Proceedings of the 56th Annual Design Automation Conference. New York: ACM, 2019: 1-6.

[189] CASSIMON A , VANNESTE S , BOSMANS S , et al. Designing resource—constrained neural networks using neural architecture search targeting embedded devices[J]. Internet of Things, 2020, 12: 100234.

[190] DUDZIAK L , CHAU T , ABDELFATTAH M , et al. BRP—NAS: Prediction—based NAS using GCNS[J]. Advances in Neural Information Processing Systems, 2020, 33: 10480-10490.

[191] LI Y W , JIN X J , MEI J R , et al. Neural architecture search for lightweight non—local networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 10297-10306.

[192] JIANG Y H , WANG X , ZHU W W . Hardware—aware transformable architecture search with efficient search space[C]// Proceedings of the IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2020: 1-6.

[193] CHEN H L , ZHUO L A , ZHANG B C , et al. Binarized neural architecture search for efficient object recognition[J]. International Journal of Computer Vision, 2021, 129: 501-516.

[194] LIBERIS E , DUDZIAK Ł , LANE N D . µNAS: Constrained neural architecture search for microcontrollers[C]// Proceedings of the 1st Workshop on Machine Learning and Systems. New York: ACM, 2021: 70-79.

[195] LOPEZ J G , AGUDO A , MORENO—NOGUER F . E—DNAS: Differentiable neural architecture search for embedded systems[C]// Proceedings of the 25th International Conference on Pattern Recognition. Piscataway: IEEE, 2021: 4704-4711.

[196] TAN M X , CHEN B , PANG R M , et al. MnasNet: Platform—aware neural architecture search for mobile[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 2820-2828.

[197] BENMEZIANE H , NIAR S , OUARNOUGHI H , et al. Pareto rank surrogate model for hardware—aware neural architecture search[C]// Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software. Piscataway: IEEE, 2022: 267-276.

[198] ZHOU A M , QU B Y , LI H , et al. Multiobjective evolutionary algorithms: A survey of the state of the art[J]. Swarm and Evolutionary Computation, 2011, 1(1): 32-49.

[199] YANG S S , TIAN Y , XIANG X S , et al. Accelerating evolutionary neural architecture search via multifidelity evaluation[J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(4): 1778-1792.

[200] XU Y , XIE L , ZHANG X , et al. PC—DARTS: Partial channel connections for memory—efficient architecture search[EB/OL]. (2020—04—07)[2025—02—17]. https://doi.org/10.48550/arXiv.1907.05737.

[201] CHU X X , ZHANG B , XU R J . FairNAS: Rethinking evaluation fairness of weight sharing neural architecture search[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 12239-12248.

[202] GUO Z , ZHANG X , MU H , et al. ProxylessNAS: Direct neural architecture search on target task and hardware[C]// International Conference on Learning Representations. Addis Ababa: ICLR, 2020: 1-13.

[203] HOWARD A , SANDLER M , CHU G , et al. Searching for MobileNetV3[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1314-1324.

[204] LIU C X , CHEN L C , SCHROFF F , et al. Auto—DeepLab: Hierarchical neural architecture search for semantic image segmentation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2019: 82-92.

[205] CHEN M H , PENG H W , FU J L , et al. AutoFormer: Searching transformers for visual recognition[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 12270-12280.

[206] WENG Y , ZHOU T B , LI Y J , et al. NAS—unet: Neural architecture search for medical image segmentation[J]. IEEE Access, 2019, 7: 44247-44257.

[207] ZHAO Y , LIU Y , JIANG B , et al. CE—NAS: An end—to—end carbon—efficient neural architecture search framework[J]. Advances in Neural Information Processing Systems, 2024, 37: 82673-82704.

[208] HOWARD A , SANDLER M , CHEN B , et al. Searching for mobileNetV3[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019: 1314-1324.

[209] LU Z C , WHALEY J , ZHU B , et al. NSGANetV2: Evolutionary multi—objective surrogate—assisted neural architecture search[C]// European Conference on Computer Vision. Cham: Springer International Publishing, 2020: 35-51.

[210] WU B A , DAI X L , ZHANG P Z , et al. FBNetV2: Differentiable neural architecture search for spatial and channel dimensions[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 12965-12974.

[211] ZHANG X , WANG Y , CHEN Z . HURRICANE: Hardware—aware neural architecture search with two—stage optimization[C]// Proceedings of the 57th ACM/IEEE Design Automation Conference. San Francisco: IEEE, 2020: 1-6.

[212] DRAAYER S , LORENZEN S S , VALSTAR M F . PAC—Bayes generalization bounds for neural architecture search[J]. Journal of Machine Learning Research, 2022, 23(120): 1-45.

[213] XU K , HU W , LESKOVEC J , et al. How powerful are graph neural networks?[C]// International Conference on Learning Representations. New Orleans: ICLR, 2019: 1-17.

[214] SMITH J , DOE A . Quantum—inspired neural architecture search with QNAS[C]// 2023 IEEE International Conference on Quantum Computing. Piscataway: IEEE, 2023: 123-135.

[215] CARRASQUILLA J , HIBAT—ALLAH M , INACK E , et al. Quantum hypernetworks: Training binary neural networks in quantum superposition[EB/OL]. (2025—07—16)[ 2025—02—17]. https://doi.org/10.48550/arXiv.2301.08292.

[216] GARNELO M , SCHWARTZWALD S , PAULUS M B . Neurosymbolic meta—learning for neural architecture search[J]. Nature Machine Intelligence, 2022, 4(7): 621-630.

[217] BARRETT C , TINELLI C . Satisfiability modulo theories[M]. Cham: Springer International Publishing, 2018: 305-343.

[218] JI W , YUE Y , WANG X , et al. Large—scale multi—objective natural computation based on dimensionality reduction and clustering[J]. Journal of System Simulation, 2023, 35(1): 41-56.

[219] YAO X , LIU Y , LIN G M . Evolutionary programming made faster[J]. IEEE Transactions on Evolutionary Computation, 1999, 3(2): 82-102.

[220] WHITE C , NEISWANGER W , SAVANI Y . BANANAS: Bayesian optimization with neural architectures for neural architecture search[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(12): 10293-10301.

[221] SIGMUND O , MAUTE K . Topology optimization approaches: A comparative review[J]. Structural and Multidisciplinary Optimization, 2013, 48(6): 1031-1055.

[222] WANG L , ZHENG N , LIU Z . MetaOASIS: Metamaterial—inspired neural architecture search[C]// Advances in Neural Information Processing Systems. Vancouver: Curran Associates, Inc., 2023: 10234-10248.

[223] PEARL J . Causality[M]. 2nd ed. Cambridge: Cambridge University Press, 2009: 45-89.

[224] LIU S , YIN J , WANG D , et al. CausalNAS: Causal inference for robust neural architecture search[C]// Proceedings of the 40th International Conference on Machine Learning. Honolulu: PMLR, 2023: 21497-21511.

[225] BONABEAU E , DORIGO M , THERAULAZ G . Swarm intelligence: From natural to artificial systems[M]. Oxford: Oxford University Press, 1999: 1-32.

[226] KIM S , KIM H , LEE J . TermiNAS: Bio—inspired neural architecture search for efficient models[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 12345-12355.

[227] CHEN T , MORENCY L P , ALAM M . Dynamic voltage and frequency scaling in neural architecture search[J]. IEEE Transactions on Computer—Aided Design, 2022, 41(8): 1949-1959.

[228] LIU D , CHENG Y , JIN X . Neural architecture search based on transformer networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision. Montreal: IEEE, 2023: 1234-1243.

[229] KIRKPATRICK J , PASCANU R , RABINOWITZ N , et al. Overcoming catastrophic forgetting in neural networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2017, 114(13): 3521-3526.

[230] CHEN T , MOREAU T , JIANG Z , et al. TVM: An automated end—to—end optimizing compiler for deep learning[C]// USENIX Symposium on Operating Systems Design and Implementation. Carlsbad: USENIX, 2018: 579-594.

[231] ZHANG Q , LIU Y , WANG H , et al. UnityNAS: Hardware—agnostic neural architecture search framework[J]. ACM Transactions on Architecture and Code Optimization, 2023, 20(2): 1-25.

[232] BI G Q , POO M M . Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type[J]. The Journal of Neuroscience, 1998, 18(24): 10464-10472.

[233] KRIZHEVSKY A , SUTSKEVER I , HINTON G . NeuroEvo: Brain—inspired neural architecture evolution[J]. Nature Machine Intelligence, 2024, 6(3): 112-125.

[234] WANG D R , SAPKOTA H , TAO Z Q , et al. Reinforced compressive neural architecture search for versatile adversarial robustness[C]// Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2024: 3001-3012.

[235] 李华, 王军, 陈志强, 等 . 跨医院医疗影像的神经架构搜索[J]. 医学影像汇刊, 2024, 43(5): 1289-1301.

[236] LI H , WANG J , CHEN Z Q , et al. Cross—hospital NAS for medical image diagnosis[J]. IEEE Transactions on Medical Imaging, 2024, 43(5): 1289-1301.

基金资助

四川省揭榜挂帅项目（重大科技专项）(2023YFG0373)