{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T15:16:37Z","timestamp":1790781397093,"version":"4.1.0"},"reference-count":139,"publisher":"Association for Computing Machinery (ACM)","issue":"11","license":[{"start":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T00:00:00Z","timestamp":1719532800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS (Differentiable ARchitecTure Search), one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focused specifically on DNAS and reviewed recent approaches in this field. Furthermore, we proposed a novel challenge-based taxonomy to classify DNAS methods. We also discussed the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we concluded by giving some insights into future research directions for the DNAS field.<\/jats:p>","DOI":"10.1145\/3665138","type":"journal-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T11:33:30Z","timestamp":1715772810000},"page":"1-36","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search"],"prefix":"10.1145","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2109-7895","authenticated-orcid":false,"given":"Alexandre","family":"Heuillet","sequence":"first","affiliation":[{"name":"Universit\u00e9 Paris-Saclay, Evry-Courcouronnes, France and Massachusetts Institute of Technology, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0664-2310","authenticated-orcid":false,"given":"Ahmad","family":"Nasser","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris-Saclay, Evry-Courcouronnes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9693-2619","authenticated-orcid":false,"given":"Hichem","family":"Arioui","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris-Saclay, Evry-Courcouronnes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1827-7150","authenticated-orcid":false,"given":"Hedi","family":"Tabia","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris-Saclay, Evry-Courcouronnes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,28]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"1","article-title":"IEEE standard for floating-point arithmetic","year":"2019","unstructured":"IEEE. 2019. IEEE standard for floating-point arithmetic. IEEE Std 754-2019 (Revision of IEEE 754-2008) (2019), 1\u201384.","journal-title":"IEEE Std 754-2019 (Revision of IEEE 754-2008)"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-82017-6_5"},{"key":"e_1_3_2_4_2","first-page":"551","article-title":"Adaptive control of a neural network with a variable function of a unit and its application","volume":"74","author":"Arai M.","year":"1991","unstructured":"M. Arai. 1991. Adaptive control of a neural network with a variable function of a unit and its application. Trans. Inst. Electron, Inform. Commun. Eng. 74 (1991), 551\u2013559.","journal-title":"Trans. Inst. Electron, Inform. Commun. Eng."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_2_6_2","first-page":"550","volume-title":"ICML","author":"Bender Gabriel","year":"2018","unstructured":"Gabriel Bender, Pieter-Jan Kindermans, Barret Zoph, Vijay Vasudevan, and Quoc Le. 2018. Understanding and simplifying one-shot architecture search. In ICML. PMLR, 550\u2013559."},{"key":"e_1_3_2_7_2","first-page":"594","volume-title":"ICML","author":"Benyahia Yassine","year":"2019","unstructured":"Yassine Benyahia, Kaicheng Yu, Kamil Bennani Smires, Martin Jaggi, Anthony C. Davison, Mathieu Salzmann, and Claudiu Musat. 2019. Overcoming multi-model forgetting. In ICML. PMLR, 594\u2013603."},{"key":"e_1_3_2_8_2","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher M.","year":"2006","unstructured":"Christopher M. Bishop and Nasser M. Nasrabadi. 2006. Pattern Recognition and Machine Learning. Vol. 4. Springer."},{"key":"e_1_3_2_9_2","volume-title":"ICLR","author":"Cai Han","year":"2020","unstructured":"Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2020. Once for all: Train one network and specialize it for efficient deployment. In ICLR."},{"key":"e_1_3_2_10_2","volume-title":"ICLR","author":"Cai Han","year":"2019","unstructured":"Han Cai, Ligeng Zhu, and Song Han. 2019. ProxylessNAS: Direct neural architecture search on target task and hardware. In ICLR."},{"key":"e_1_3_2_11_2","volume-title":"Explainable Neural Architecture Search (XNAS)","author":"Carmichael Zachariah J.","year":"2021","unstructured":"Zachariah J. Carmichael, Timothy Y. Moon, and Samson A. Jacobs. 2021. Explainable Neural Architecture Search (XNAS). Technical Report. Lawrence Livermore National Lab.(LLNL), Livermore, CA (United States)."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(96)00006-8"},{"key":"e_1_3_2_13_2","first-page":"2463","volume-title":"IJCAI","author":"Chen Daoyuan","year":"2021","unstructured":"Daoyuan Chen, Yaliang Li, Minghui Qiu, Zhen Wang, Bofang Li, Bolin Ding, Hongbo Deng, Jun Huang, Wei Lin, and Jingren Zhou. 2021. AdaBERT: Task-adaptive BERT compression with differentiable neural architecture search. In IJCAI. 2463\u20132469."},{"key":"e_1_3_2_14_2","volume-title":"ICLR","author":"Chen Wuyang","year":"2021","unstructured":"Wuyang Chen, Xinyu Gong, and Zhangyang Wang. 2021. Neural architecture search on ImageNet in four GPU hours: A theoretically inspired perspective. In ICLR."},{"key":"e_1_3_2_15_2","first-page":"1554","volume-title":"ICML","author":"Chen Xiangning","year":"2020","unstructured":"Xiangning Chen and Cho-Jui Hsieh. 2020. Stabilizing differentiable architecture search via perturbation-based regularization. In ICML. PMLR, 1554\u20131565."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00138"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00492"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_20_2","volume-title":"ICLR","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, and Junchi Yan. 2021. DARTS-: Robustly stepping out of performance collapse without indicators. In ICLR."},{"key":"e_1_3_2_21_2","volume-title":"BMVC","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu and Bo Zhang. 2021. Noisy differentiable architecture search. In BMVC."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"e_1_3_2_23_2","first-page":"2048","volume-title":"ICML","author":"Cobbe Karl","year":"2020","unstructured":"Karl Cobbe, Chris Hesse, Jacob Hilton, and John Schulman. 2020. Leveraging procedural generation to benchmark reinforcement learning. In ICML. PMLR, 2048\u20132056."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/10667"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01601"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_28_2","unstructured":"Terrance DeVries and Graham W. Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"e_1_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Shaojin Ding Tianlong Chen Xinyu Gong Weiwei Zha and Zhangyang Wang. 2020. AutoSpeech: Neural architecture search for speaker recognition. arXiv preprint arXiv:2005.03215 (2020).","DOI":"10.21437\/Interspeech.2020-1258"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2976694"},{"key":"e_1_3_2_31_2","volume-title":"ICLR","author":"Dong Xuanyi","year":"2020","unstructured":"Xuanyi Dong and Yi Yang. 2020. NAS-bench-201: Extending the scope of reproducible neural architecture search. In ICLR. Retrieved from https:\/\/openreview.net\/forum?id=HJxyZkBKDr"},{"key":"e_1_3_2_32_2","unstructured":"Martin Ebers. 2020. Regulating explainable AI in the European Union. An overview of the current legal framework (s). Nordic Yearbook of Law and Informatics Liane Colonna\/Stanley Greenstein (Eds.). (2020)."},{"key":"e_1_3_2_33_2","first-page":"1407","volume-title":"ICML","author":"Espeholt Lasse","year":"2018","unstructured":"Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Vlad Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, et\u00a0al. 2018. IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures. In ICML. PMLR, 1407\u20131416."},{"key":"e_1_3_2_34_2","first-page":"1","article-title":"The PASCAL visual object classes challenge 2012 (VOC2012) development kit","volume":"2007","author":"Everingham Mark","year":"2012","unstructured":"Mark Everingham and John Winn. 2012. The PASCAL visual object classes challenge 2012 (VOC2012) development kit. Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep 2007 (2012), 1\u201345.","journal-title":"Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107968"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01064"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00572"},{"key":"e_1_3_2_38_2","article-title":"Deep active learning with a neural architecture search","volume":"32","author":"Geifman Yonatan","year":"2019","unstructured":"Yonatan Geifman and Ran El-Yaniv. 2019. Deep active learning with a neural architecture search. Advan. Neural Inf. Process. Syst. 32 (2019).","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_39_2","first-page":"17129","article-title":"CLEARER: Multi-scale neural architecture search for image restoration","volume":"33","author":"Gou Yuanbiao","year":"2020","unstructured":"Yuanbiao Gou, Boyun Li, Zitao Liu, Songfan Yang, and Xi Peng. 2020. CLEARER: Multi-scale neural architecture search for image restoration. Advan. Neural Inf. Process. Syst. 33 (2020), 17129\u201317140.","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_40_2","volume-title":"ICLR","author":"Greff Klaus","year":"2017","unstructured":"Klaus Greff, Rupesh K. Srivastava, and J\u00fcrgen Schmidhuber. 2017. Highway and residual networks learn unrolled iterative estimation. In ICLR."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01213"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00428"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"W. Keith Hastings. 1970. Monte Carlo sampling methods using Markov chains and their applications. Biometrika 57 1 (1970) 97\u2013109.","DOI":"10.1093\/biomet\/57.1.97"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"e_1_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Alexandre Heuillet Hedi Tabia and Hichem Arioui. 2023. NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks. Retrieved from https:\/\/openreview.net\/forum?id=apZRm_0VClK","DOI":"10.1016\/j.procs.2023.08.144"},{"key":"e_1_3_2_47_2","unstructured":"Alexandre Heuillet Hedi Tabia Hichem Arioui and Kamal Youcef-Toumi. 2021. D-DARTS: Distributed differentiable architecture search. arXiv preprint arXiv:2108.09306 (2021)."},{"key":"e_1_3_2_48_2","volume-title":"NIPS","author":"Hosseini Ramtin","year":"2022","unstructured":"Ramtin Hosseini and Pengtao Xie. 2022. Saliency-aware neural architecture search. In NIPS."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01210"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153253"},{"key":"e_1_3_2_51_2","unstructured":"Han Huang Li Shen Chaoyang He Weisheng Dong Haozhi Huang and Guangming Shi. 2021. Lightweight image super-resolution with hierarchical and differentiable neural architecture search. arXiv preprint arXiv:2105.03939 (2021)."},{"key":"e_1_3_2_52_2","volume-title":"Medical Imaging with Deep Learning","author":"Huang Ziyan","year":"2021","unstructured":"Ziyan Huang, Zehua Wang, Lixu Gu, and Zhikai Yang. 2021. AdwU-Net: Adaptive depth and width U-Net for medical image segmentation by differentiable neural architecture search. In Medical Imaging with Deep Learning."},{"key":"e_1_3_2_53_2","volume-title":"ICLR","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparametrization with Gumble-softmax. In ICLR."},{"key":"e_1_3_2_54_2","unstructured":"Qian Jiang Xiaofan Zhang Deming Chen Minh N. Do and Raymond A. Yeh. 2021. EH-DNAS: End-to-end hardware-aware differentiable neural architecture search. arXiv preprint arXiv:2111.12299 (2021)."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1367"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330648"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3527850"},{"key":"e_1_3_2_58_2","article-title":"Neural architecture search with Bayesian optimization and optimal transport","volume":"31","author":"Kandasamy Kirthevasan","year":"2018","unstructured":"Kirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabas Poczos, and Eric P. Xing. 2018. Neural architecture search with Bayesian optimization and optimal transport. Advan. Neural Inf. Process. Syst. 31 (2018).","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_59_2","first-page":"4171","volume-title":"NAACL-HLT","author":"Kenton Jacob Devlin Ming-Wei Chang","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_60_2","first-page":"1344","volume-title":"DATE","author":"Kim Sunghoon","year":"2021","unstructured":"Sunghoon Kim, Hyunjeong Kwon, Eunji Kwon, Youngchang Choi, Tae-Hyun Oh, and Seokhyeong Kang. 2021. MDARTS: Multi-objective differentiable neural architecture search. In DATE. IEEE, 1344\u20131349."},{"key":"e_1_3_2_61_2","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. (2009)."},{"issue":"10","key":"e_1_3_2_62_2","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun Yann","year":"1995","unstructured":"Yann LeCun and Yoshua Bengio. 1995. Convolutional networks for images, speech, and time series. Handb. Brain Theor. Neural Netw. 3361, 10 (1995), 1995.","journal-title":"Handb. Brain Theor. Neural Netw."},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"254","key":"e_1_3_2_64_2","first-page":"10","article-title":"Cauchy and the gradient method","volume":"251","author":"Lemar\u00e9chal Claude","year":"2012","unstructured":"Claude Lemar\u00e9chal. 2012. Cauchy and the gradient method. Doc. Math. Extra 251, 254 (2012), 10.","journal-title":"Doc. Math. Extra"},{"key":"e_1_3_2_65_2","first-page":"367","volume-title":"Uncertainty in Artificial Intelligence","author":"Li Liam","year":"2020","unstructured":"Liam Li and Ameet Talwalkar. 2020. Random search and reproducibility for neural architecture search. In Uncertainty in Artificial Intelligence. PMLR, 367\u2013377."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.101974"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3083739"},{"key":"e_1_3_2_68_2","first-page":"950","volume-title":"IET IRC\u201920)","author":"Li Zhiheng","year":"2020","unstructured":"Zhiheng Li, Liang Chen, Xiaoqi Huang, Zhixin Zhang, and Hao Shi. 2020. Differentiable neural architecture search for sar image ship object detection. In IET IRC\u201920). IET, 950\u2013954."},{"key":"e_1_3_2_69_2","unstructured":"Hanwen Liang Shifeng Zhang Jiacheng Sun Xingqiu He Weiran Huang Kechen Zhuang and Zhenguo Li. 2019. DARTS+: Improved differentiable architecture search with early stopping. arXiv preprint arXiv:1909.06035 (2019)."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00093"},{"key":"e_1_3_2_74_2","volume-title":"ICLR","author":"Liu Hanxiao","year":"2019","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2019. DARTS: Differentiable architecture search. In ICLR."},{"key":"e_1_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Vasco Lopes Miguel Santos Bruno Degardin and Lu\u00eds A. Alexandre. 2021. Guided evolution for neural architecture search. arXiv preprint arXiv:2110.15232 (2021).","DOI":"10.1145\/3520304.3528936"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412130"},{"key":"e_1_3_2_77_2","first-page":"1540","volume-title":"AISTATS","author":"Lorraine Jonathan","year":"2020","unstructured":"Jonathan Lorraine, Paul Vicol, and David Duvenaud. 2020. Optimizing millions of hyperparameters by implicit differentiation. In AISTATS. PMLR, 1540\u20131552."},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_58"},{"key":"e_1_3_2_79_2","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advan. Neural Inf. Process. Syst. 30 (2017).","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_80_2","article-title":"LightNAS: On lightweight and scalable neural architecture search for embedded platforms","author":"Luo Xiangzhong","year":"2022","unstructured":"Xiangzhong Luo, Di Liu, Hao Kong, Shuo Huai, Hui Chen, and Weichen Liu. 2022. LightNAS: On lightweight and scalable neural architecture search for embedded platforms. IEEE Trans. Comput.-aid. Des. Integ. Circ. Syst. 42, 6 (2022).","journal-title":"IEEE Trans. Comput.-aid. Des. Integ. Circ. Syst."},{"issue":"2","key":"e_1_3_2_81_2","first-page":"313330","article-title":"Building a large annotated corpus of English: The Penn Treebank","volume":"19","author":"Marcus Mitchell P.","year":"1993","unstructured":"Mitchell P. Marcus, Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Comput. Linguist. 19, 2 (June1993), 313330.","journal-title":"Comput. Linguist."},{"key":"e_1_3_2_82_2","volume-title":"British Machine Vision Conference","author":"Marvasti-Zadeh Seyed Mojtaba","year":"2021","unstructured":"Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Li Cheng, Hossein Ghanei-Yakhdan, and Shohreh Kasaei. 2021. CHASE: Robust visual tracking via cell-level differentiable neural architecture search. In British Machine Vision Conference."},{"key":"e_1_3_2_83_2","first-page":"7588","volume-title":"ICML","author":"Mellor Joe","year":"2021","unstructured":"Joe Mellor, Jack Turner, Amos Storkey, and Elliot J. Crowley. 2021. Neural architecture search without training. In ICML. PMLR, 7588\u20137598."},{"key":"e_1_3_2_84_2","volume-title":"ICLR","author":"Merity Stephen","year":"2017","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. 2017. Pointer sentinel mixture models. In ICLR. Retrieved from https:\/\/openreview.net\/forum?id=Byj72udxe"},{"key":"e_1_3_2_85_2","unstructured":"Yingjie Miao Xingyou Song Daiyi Peng Summer Yue John D. Co-Reyes Eugene Brevdo and Aleksandra Faust. 2021. RL-DARTS: Differentiable architecture search for reinforcement learning. arXiv preprint arXiv:2106.02229 (2021)."},{"key":"e_1_3_2_86_2","volume-title":"ICLR","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed precision training. In ICLR."},{"key":"e_1_3_2_87_2","volume-title":"Neural Network Intelligence","year":"2021","unstructured":"Microsoft. 2021. Neural Network Intelligence. Retrieved from https:\/\/github.com\/microsoft\/nni"},{"key":"e_1_3_2_88_2","first-page":"1982","article-title":"Neural architecture search for keyword spotting","author":"Mo Tong","year":"2020","unstructured":"Tong Mo, Yakun Yu, Mohammad Salameh, Di Niu, and Shangling Jui. 2020. Neural architecture search for keyword spotting. In Interspeech. 1982\u20131986.","journal-title":"Interspeech"},{"key":"e_1_3_2_89_2","unstructured":"Niv Nayman Yonathan Aflalo Asaf Noy Rong Jin and Lihi Zelnik-Manor. 2021. BINAS: Bilinear interpretable neural architecture search. arXiv preprint arXiv:2110.12399 (2021)."},{"key":"e_1_3_2_90_2","first-page":"7979","volume-title":"ICML","author":"Nayman Niv","year":"2021","unstructured":"Niv Nayman, Yonathan Aflalo, Asaf Noy, and Lihi Zelnik. 2021. HardCoRe-NAS: Hard constrained differentiable neural architecture search. In ICML. PMLR, 7979\u20137990."},{"key":"e_1_3_2_91_2","unstructured":"Yuval Netzer Tao Wang Adam Coates Alessandro Bissacco Bo Wu and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011 5 (2011) 7."},{"key":"e_1_3_2_92_2","first-page":"493","volume-title":"AISTATS","author":"Noy Asaf","year":"2020","unstructured":"Asaf Noy, Niv Nayman, Tal Ridnik, Nadav Zamir, Sivan Doveh, Itamar Friedman, Raja Giryes, and Lihi Zelnik. 2020. ASAP: Architecture search, anneal and prune. In AISTATS. PMLR, 493\u2013503."},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3020424"},{"key":"e_1_3_2_94_2","article-title":"ReCNAS: Resource-constrained neural architecture search based on differentiable annealing and dynamic pruning","author":"Peng Cheng","year":"2022","unstructured":"Cheng Peng, Yangyang Li, Ronghua Shang, and Licheng Jiao. 2022. ReCNAS: Resource-constrained neural architecture search based on differentiable annealing and dynamic pruning. IEEE Trans. Neural Netw. Learn. Syst. 35, 2 (2022).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802919"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"e_1_3_2_97_2","unstructured":"Michael Ruchte Arber Zela Julien Siems Josif Grabocka and Frank Hutter. 2020. NASLib: A modular and flexible neural architecture search library. Retrieved from https:\/\/github.com\/automl\/NASLib"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_100_2","article-title":"A value for n-person games","volume":"69","author":"Shapley Lloyd S.","year":"1997","unstructured":"Lloyd S. Shapley. 1997. A value for n-person games. Class. Game Theor. 69 (1997).","journal-title":"Class. Game Theor."},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_102_2","first-page":"10096","volume-title":"ICML","author":"Tan Mingxing","year":"2021","unstructured":"Mingxing Tan and Quoc Le. 2021. EfficientNetV2: Smaller models and faster training. In ICML. PMLR, 10096\u201310106."},{"key":"e_1_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01128"},{"key":"e_1_3_2_105_2","first-page":"1","volume-title":"IJCNN","author":"Wyk Gerard Jacques van","year":"2019","unstructured":"Gerard Jacques van Wyk and Anna Sergeevna Bosman. 2019. Evolutionary neural architecture search for image restoration. In IJCNN. IEEE, 1\u20138."},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01298"},{"key":"e_1_3_2_107_2","volume-title":"ICLR","author":"Wang Ruochen","year":"2021","unstructured":"Ruochen Wang, Minhao Cheng, Xiangning Chen, Xiaocheng Tang, and Cho-Jui Hsieh. 2021. Rethinking architecture selection in differentiable NAS. In ICLR."},{"key":"e_1_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01209"},{"key":"e_1_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-020-01048-4"},{"key":"e_1_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908991"},{"key":"e_1_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_113_2","unstructured":"Bichen Wu Chaojian Li Hang Zhang Xiaoliang Dai Peizhao Zhang Matthew Yu Jialiang Wang Yingyan Lin and Peter Vajda. 2021. FBNetV5: Neural architecture search for multiple tasks in one run. arXiv preprint arXiv:2111.10007 (2021)."},{"key":"e_1_3_2_114_2","unstructured":"Dongxian Wu Yisen Wang and Shu-tao Xia. 2020. Revisiting loss landscape for adversarial robustness. arXiv preprint arXiv:2004.05884 (2020)."},{"key":"e_1_3_2_115_2","unstructured":"Yan Wu Zhiwu Huang Suryansh Kumar Rhea Sanjay Sukthanker Radu Timofte and Luc Van Gool. 2021. Trilevel neural architecture search for efficient single image super-resolution. arXiv preprint arXiv:2101.06658 (2021)."},{"key":"e_1_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_117_2","unstructured":"Sirui Xie Hehui Zheng Chunxiao Liu and Liang Lin. 2018. SNAS: Stochastic neural architecture search. arXiv preprint arXiv:1812.09926 (2018)."},{"key":"e_1_3_2_118_2","unstructured":"Jingjing Xu Wangchunshu Zhou Zhiyi Fu Hao Zhou and Lei Li. 2021. A survey on green deep learning. arXiv preprint arXiv:2111.05193 (2021)."},{"key":"e_1_3_2_119_2","volume-title":"ICLR","author":"Xu Yuhui","year":"2020","unstructured":"Yuhui Xu, Lingxi Xie, Xiaopeng Zhang, Xin Chen, Guo-Jun Qi, Qi Tian, and Hongkai Xiong. 2020. PC-DARTS: Partial channel connections for memory-efficient architecture search. In ICLR."},{"key":"e_1_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712499"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00660"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01060"},{"key":"e_1_3_2_123_2","article-title":"Cyclic differentiable architecture search","author":"Yu Hongyuan","year":"2022","unstructured":"Hongyuan Yu, Houwen Peng, Yan Huang, Jianlong Fu, Hao Du, Liang Wang, and Haibin Ling. 2022. Cyclic differentiable architecture search. IEEE Trans. Pattern Anal. Mach. Intell. 45, 1 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_41"},{"key":"e_1_3_2_125_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00418"},{"key":"e_1_3_2_126_2","doi-asserted-by":"crossref","unstructured":"Ahmet Caner Y\u00fcz\u00fcg\u00fcler Nikolaos Dimitriadis and Pascal Frossard. 2022. U-boost NAS: Utilization-boosted differentiable neural architecture search. arXiv preprint arXiv:2203.12412 (2022).","DOI":"10.1007\/978-3-031-19775-8_11"},{"key":"e_1_3_2_127_2","volume-title":"ICLR","author":"Zela Arber","year":"2020","unstructured":"Arber Zela, Thomas Elsken, Tonmoy Saikia, Yassine Marrakchi, Thomas Brox, and Frank Hutter. 2020. Understanding and robustifying differentiable architecture search. In ICLR."},{"key":"e_1_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00371"},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2021.107773"},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00354"},{"key":"e_1_3_2_131_2","first-page":"13341","article-title":"Differentiable neural architecture search in equivalent space with exploration enhancement","volume":"33","author":"Zhang Miao","year":"2020","unstructured":"Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Zongyuan Ge, and Steven Su. 2020. Differentiable neural architecture search in equivalent space with exploration enhancement. Advan. Neural Inf. Process. Syst. 33 (2020), 13341\u201313351.","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_132_2","first-page":"12557","volume-title":"ICML","author":"Zhang Miao","year":"2021","unstructured":"Miao Zhang, Steven W. Su, Shirui Pan, Xiaojun Chang, Ehsan M. Abbasnejad, and Reza Haffari. 2021. IDARTS: Differentiable architecture search with stochastic implicit gradients. In ICML. PMLR, 12557\u201312566."},{"key":"e_1_3_2_133_2","first-page":"1","article-title":"Self-trained target detection of radar and sonar images using automatic deep learning","volume":"60","author":"Zhang Peng","year":"2021","unstructured":"Peng Zhang, Jinsong Tang, Heping Zhong, Mingqiang Ning, Dandan Liu, and Ke Wu. 2021. Self-trained target detection of radar and sonar images using automatic deep learning. IEEE Trans. Geosci. Rem. Sens. 60 (2021), 1\u201314.","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0214-z"},{"key":"e_1_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383527"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_137_2","first-page":"8296","article-title":"Theory-inspired path-regularized differential network architecture search","volume":"33","author":"Zhou Pan","year":"2020","unstructured":"Pan Zhou, Caiming Xiong, Richard Socher, and Steven Chu Hong Hoi. 2020. Theory-inspired path-regularized differential network architecture search. Advan. Neural Inf. Process. Syst. 33 (2020), 8296\u20138307.","journal-title":"Advan. Neural Inf. Process. Syst."},{"key":"e_1_3_2_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00035"},{"key":"e_1_3_2_139_2","volume-title":"ICLR","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc Le. 2017. Neural architecture search with reinforcement learning. In ICLR."},{"key":"e_1_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665138","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:33Z","timestamp":1750294713000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,28]]},"references-count":139,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3665138"],"URL":"https:\/\/doi.org\/10.1145\/3665138","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,28]]},"assertion":[{"value":"2022-12-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-11","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}