{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:33:22Z","timestamp":1784738002606,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"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":[],"published-print":{"date-parts":[[2023,12,14]]},"DOI":"10.1145\/3659154.3659161","type":"proceedings-article","created":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T12:17:39Z","timestamp":1735215459000},"page":"30-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Rank-based Training-Free NAS Algorithm"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4867-3835","authenticated-orcid":false,"given":"Cheng-Han","family":"Hsieh","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0128-4052","authenticated-orcid":false,"given":"Chun-Wei","family":"Tsai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,12,26]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"B.\u00a0Zoph and Q.\u00a0V. Le \u201cNeural architecture search with reinforcement learning \u201d arXiv preprint pp. 1\u201316 2016."},{"key":"e_1_3_3_1_3_2","unstructured":"Z.\u00a0Sun M.\u00a0Lin X.\u00a0Sun Z.\u00a0Tan H.\u00a0Li and R.\u00a0Jin \u201cMAE-DET: Revisiting maximum entropy principle in zero-shot NAS for efficient object detection \u201d in Proceedings of the International Conference on Machine Learning 2022 pp. 20\u00a0810\u201320\u00a0826."},{"key":"e_1_3_3_1_4_2","unstructured":"J.\u00a0Mellor J.\u00a0Turner A.\u00a0Storkey and E.\u00a0J. Crowley \u201cNeural architecture search without training \u201d in Proceedings of the International Conference on Machine Learning 2021 pp. 7588\u20137598."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"H.\u00a0Zheng K.\u00a0An and Z.\u00a0Ou \u201cEfficient neural architecture search for end-to-end speech recognition via straight-through gradients \u201d in Proceedings of the IEEE Spoken Language Technology Workshop 2021 pp. 60\u201367.","DOI":"10.1109\/SLT48900.2021.9383527"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Jiang C.\u00a0Hu T.\u00a0Xiao C.\u00a0Zhang and J.\u00a0Zhu \u201cImproved differentiable architecture search for language modeling and named entity recognition \u201d in Proceedings of the Conference on Empirical Methods in Natural Language Processing 2019 pp. 3585\u20133590.","DOI":"10.18653\/v1\/D19-1367"},{"key":"e_1_3_3_1_7_2","unstructured":"H.\u00a0Tanaka D.\u00a0Kunin D.\u00a0L. Yamins and S.\u00a0Ganguli \u201cPruning neural networks without any data by iteratively conserving synaptic flow \u201d in Proceedings of the Conference on Neural Information Processing Systems vol.\u00a033 2020 pp. 6377\u20136389."},{"key":"e_1_3_3_1_8_2","unstructured":"M.\u00a0S. Abdelfattah A.\u00a0Mehrotra \u0141.\u00a0Dudziak and N.\u00a0D. Lane \u201cZero-cost proxies for lightweight NAS \u201d in Proceedings of the International Conference on Learning Representations 2021 pp. 1\u201317."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"N.\u00a0Cavagnero L.\u00a0Robbiano B.\u00a0Caputo and G.\u00a0Averta \u201cFreeREA: Training-free evolution-based architecture search \u201d in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision 2023 pp. 1493\u20131502.","DOI":"10.1109\/WACV56688.2023.00154"},{"key":"e_1_3_3_1_10_2","unstructured":"W.\u00a0Chen X.\u00a0Gong and Z.\u00a0Wang \u201cNeural architecture search on imagenet in four gpu hours: A theoretically inspired perspective \u201d in Proceedings of the International Conference on Learning Representations 2021 pp. 1\u201315."},{"key":"e_1_3_3_1_11_2","unstructured":"Y.\u00a0Shu S.\u00a0Cai Z.\u00a0Dai B.\u00a0C. Ooi and B.\u00a0K.\u00a0H. Low \u201cNASI: Label- and data-agnostic neural architecture search at initialization \u201d arXiv preprint pp. 1\u20138 2021."},{"key":"e_1_3_3_1_12_2","unstructured":"M.-T. Wu H.-I. Lin and C.-W. Tsai \u201cA training-free neural architecture search algorithm based on search economics \u201d IEEE Transactions on Evolutionary Computation pp. 1\u201315 2023 In Press."},{"key":"e_1_3_3_1_13_2","unstructured":"N.\u00a0Lee T.\u00a0Ajanthan and P.\u00a0Torr \u201cSNIP: Single-shot network pruning based on connection sensitivity \u201d in Proceedings of the International Conference on Learning Representations 2019 pp. 1\u201315."},{"key":"e_1_3_3_1_14_2","unstructured":"C.\u00a0Wang G.\u00a0Zhang and R.\u00a0Grosse \u201cPicking winning tickets before training by preserving gradient flow \u201d in Proceedings of the International Conference on Learning Representations 2020 pp. 1\u201311."},{"key":"e_1_3_3_1_15_2","unstructured":"A.\u00a0Jacot F.\u00a0Gabriel and C.\u00a0Hongler \u201cNeural tangent kernel: Convergence and generalization in neural networks \u201d in Proceedings of the International Conference on Neural Information Processing Systems 2018 pp. 8580\u20138589."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"V.\u00a0Lopes S.\u00a0Alirezazadeh and L.\u00a0A. Alexandre \u201cEPE-NAS: Efficient performance estimation without training for neural architecture search \u201d in Proceedings of the International Conference on Artificial Neural Networks 2021 pp. 552\u2013563.","DOI":"10.1007\/978-3-030-86383-8_44"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"C.-W. Tsai \u201cSearch economics: A solution space and computing resource aware search method \u201d in Proceedings of the International Conference on Systems Man and Cybernetics 2015 pp. 2555\u20132560.","DOI":"10.1109\/SMC.2015.447"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"M.-T. Wu H.-I. Lin and C.-W. Tsai \u201cA training-free genetic neural architecture search \u201d in Proceedings of the ACM International Conference on Intelligent Computing and its Emerging Applications 2021 pp. 65\u201370.","DOI":"10.1145\/3491396.3506510"},{"key":"e_1_3_3_1_19_2","unstructured":"M.\u00a0Lin P.\u00a0Wang Z.\u00a0Sun H.\u00a0Chen X.\u00a0Sun Q.\u00a0Qian H.\u00a0Li and R.\u00a0Jin \u201cZen-NAS: A zero-shot NAS for high-performance deep image recognition \u201d in Proceedings of the International Conference on Machine Learning 2022 pp. 20\u00a0810\u201320\u00a0826."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"E.\u00a0Real A.\u00a0Aggarwal Y.\u00a0Huang and Q.\u00a0V. Le \u201cRegularized evolution for image classifier architecture search \u201d in Proceedings of the AAAI Conference on Artificial Intelligence vol.\u00a033 no.\u00a01 2019 pp. 4780\u20134789.","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"R.\u00a0J. Williams \u201cSimple statistical gradient-following algorithms for connectionist reinforcement learning \u201d Machine learning vol.\u00a08 pp. 229\u2013256 1992.","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_3_1_22_2","unstructured":"S.\u00a0Falkner A.\u00a0Klein and F.\u00a0Hutter \u201cBohb: Robust and efficient hyperparameter optimization at scale \u201d in Proceedings of the International Conference on Machine Learning 2018 pp. 1437\u20131446."},{"key":"e_1_3_3_1_23_2","unstructured":"L.\u00a0Li and A.\u00a0Talwalkar \u201cRandom search and reproducibility for neural architecture search \u201d in Proceedings of the Conference on Uncertainty in artificial intelligence 2020 pp. 367\u2013377."},{"key":"e_1_3_3_1_24_2","unstructured":"H.\u00a0Liu K.\u00a0Simonyan and Y.\u00a0Yang \u201cDARTS: Differentiable architecture search \u201d in Proceedings of the International Conference on Learning Representations 2019 pp. 1\u201313."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"X.\u00a0Dong and Y.\u00a0Yang \u201cSearching for a robust neural architecture in four GPU hours \u201d in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2019 pp. 1761\u20131770.","DOI":"10.1109\/CVPR.2019.00186"},{"key":"e_1_3_3_1_26_2","unstructured":"\u2014\u2014 \u201cOne-shot neural architecture search via self-evaluated template network \u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision 2019 pp. 3681\u20133690."},{"key":"e_1_3_3_1_27_2","unstructured":"H.\u00a0Pham M.\u00a0Y. Guan B.\u00a0Zoph Q.\u00a0V. Le and J.\u00a0Dean \u201cEfficient neural architecture search via parameter sharing \u201d in Proceedings of the International Conference on Machine Learning 2018 pp. 4095\u20134104."},{"key":"e_1_3_3_1_28_2","unstructured":"X.\u00a0Dong L.\u00a0Liu K.\u00a0Musial and B.\u00a0Gabrys \u201cNATS-bench: Benchmarking NAS algorithms for architecture topology and size \u201d IEEE Transactions on Pattern Analysis and Machine Intelligence vol.\u00a044 no.\u00a07 pp. 3634\u20133646 2022."},{"key":"e_1_3_3_1_29_2","unstructured":"C.\u00a0Ying A.\u00a0Klein E.\u00a0Christiansen E.\u00a0Real K.\u00a0Murphy and F.\u00a0Hutter \u201cNAS-bench-101: Towards reproducible neural architecture search \u201d in Proceedings of the International Conference on Machine Learning vol.\u00a097 2019 pp. 7105\u20137114."},{"key":"e_1_3_3_1_30_2","unstructured":"X.\u00a0Dong and Y.\u00a0Yang \u201cNAS-bench-201: Extending the scope of reproducible neural architecture search \u201d in Proceedings of the International Conference on Learning Representations 2020 pp. 1\u201316."}],"event":{"name":"ICEA 2023: The 2023 International Conference on Intelligent Computing and Its Emerging Applications","location":"Kaohsiung Taiwan","acronym":"ICEA 2023"},"container-title":["Proceedings of the 2023 International Conference on Intelligent Computing and Its Emerging Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659154.3659161","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3659154.3659161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:14Z","timestamp":1750290254000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659154.3659161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"references-count":29,"alternative-id":["10.1145\/3659154.3659161","10.1145\/3659154"],"URL":"https:\/\/doi.org\/10.1145\/3659154.3659161","relation":{},"subject":[],"published":{"date-parts":[[2023,12,14]]},"assertion":[{"value":"2024-12-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}