{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:09:31Z","timestamp":1775786971658,"version":"3.50.1"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T00:00:00Z","timestamp":1681516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2023,6,30]]},"abstract":"<jats:p>\n            Deep learning (DL) models such as convolutional neural networks (ConvNets) are being deployed to solve various computer vision and natural language processing tasks at the edge. It is a challenge to find the right DL architecture that simultaneously meets the accuracy, power, and performance budgets of such resource-constrained devices. Hardware-aware Neural Architecture Search (HW-NAS) has recently gained steam by automating the design of efficient DL models for a variety of target hardware platforms. However, such algorithms require excessive computational resources. Thousands of GPU days are required to evaluate and explore an architecture search space such as FBNet\u00a0[\n            <jats:xref ref-type=\"bibr\">45<\/jats:xref>\n            ]. State-of-the-art approaches propose using surrogate models to predict architecture accuracy and hardware performance to speed up HW-NAS. Existing approaches use independent surrogate models to estimate each objective, resulting in non-optimal Pareto fronts. In this article, HW-PR-NAS,\n            <jats:xref ref-type=\"fn\">\n              <jats:sup>1<\/jats:sup>\n            <\/jats:xref>\n            a novel Pareto rank-preserving surrogate model for edge computing platforms, is presented. Our model integrates a new loss function that ranks the architectures according to their Pareto rank, regardless of the actual values of the various objectives. We employ a simple yet effective surrogate model architecture that can be generalized to any standard DL model. We then present an optimized evolutionary algorithm that uses and validates our surrogate model. Our approach has been evaluated on seven edge hardware platforms from various classes, including ASIC, FPGA, GPU, and multi-core CPU. The evaluation results show that HW-PR-NAS achieves up to 2.5\u00d7 speedup compared to state-of-the-art methods while achieving 98% near the actual Pareto front.\n          <\/jats:p>","DOI":"10.1145\/3579853","type":"journal-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T12:02:35Z","timestamp":1673438555000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Multi-objective Hardware-aware Neural Architecture Search with Pareto Rank-preserving Surrogate Models"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5259-0749","authenticated-orcid":false,"given":"Hadjer","family":"Benmeziane","sequence":"first","affiliation":[{"name":"Univ. Polytechnique Hauts-de-France, Valenciennes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7490-5350","authenticated-orcid":false,"given":"Hamza","family":"Ouarnoughi","sequence":"additional","affiliation":[{"name":"Univ. Polytechnique Hauts-de-France, Valenciennes, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-8749","authenticated-orcid":false,"given":"Kaoutar","family":"El Maghraoui","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7550-484X","authenticated-orcid":false,"given":"Smail","family":"Niar","sequence":"additional","affiliation":[{"name":"Univ. Polytechnique Hauts-de-France, Valenciennes, France"}]}],"member":"320","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022327"},{"key":"e_1_3_2_3_2","article-title":"A comprehensive survey on hardware-aware neural architecture search","volume":"2101","author":"Benmeziane Hadjer","year":"2021","unstructured":"Hadjer Benmeziane, Kaoutar El Maghraoui, Hamza Ouarnoughi, Sma\u00efl Niar, Martin Wistuba, and Naigang Wang. 2021. A comprehensive survey on hardware-aware neural architecture search. CoRR abs\/2101.09336 (2021).","journal-title":"CoRR"},{"key":"e_1_3_2_4_2","volume-title":"IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS\u201922)","author":"Benmeziane Hadjer","year":"2022","unstructured":"Hadjer Benmeziane, Smail Niar, Hamza Ouarnoughi, and Kaoutar El Maghraoui. 2022. Pareto rank surrogate model for hardware-aware neural architecture search. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS\u201922)."},{"key":"e_1_3_2_5_2","first-page":"21:1\u201321:6","volume-title":"The 7th Annual International Conference on Arab Women","author":"Benmeziane Hadjer","year":"2021","unstructured":"Hadjer Benmeziane, Hamza Ouarnoughi, Kaoutar El Maghraoui, and Sma\u00efl Niar. 2021. Accelerating neural architecture search with rank-preserving surrogate models. In The 7th Annual International Conference on Arab Women. ACM, 21:1\u201321:6."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"e_1_3_2_7_2","volume-title":"8th International Conference on Learning Representations (ICLR\u201920)","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 8th International Conference on Learning Representations (ICLR\u201920). OpenReview.net. https:\/\/openreview.net\/forum?id=HylxE1HKwS."},{"key":"e_1_3_2_8_2","volume-title":"7th International Conference on Learning Representations","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 7th International Conference on Learning Representations."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004005"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"e_1_3_2_12_2","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","volume":"1707","author":"Chrabaszcz Patryk","year":"2017","unstructured":"Patryk Chrabaszcz, Ilya Loshchilov, and Frank Hutter. 2017. A downsampled variant of ImageNet as an alternative to the CIFAR datasets. CoRR abs\/1707.08819 (2017). arXiv:1707.08819http:\/\/arxiv.org\/abs\/1707.08819","journal-title":"CoRR"},{"key":"e_1_3_2_13_2","first-page":"16276","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201921)","author":"Dai Xiaoliang","year":"2021","unstructured":"Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Bichen Wu, Zijian He, Zhen Wei, Kan Chen, Yuandong Tian, Matthew Yu, Peter Vajda, and Joseph E. Gonzalez. 2021. FBNetV3: Joint architecture-recipe search using predictor pretraining. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201921). Computer Vision Foundation\/IEEE, 16276\u201316285."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747295"},{"key":"e_1_3_2_16_2","volume-title":"8th International Conference on Learning Representations (ICLR\u201920)","author":"Dong Xuanyi","year":"2020","unstructured":"Xuanyi Dong and Yi Yang. 2020. NAS-Bench-201: Extending the scope of reproducible neural architecture search. In 8th International Conference on Learning Representations (ICLR\u201920). OpenReview.net."},{"key":"e_1_3_2_17_2","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems","author":"Dudziak Lukasz","year":"2020","unstructured":"Lukasz Dudziak, Thomas C. P. Chau, Mohamed S. Abdelfattah, Royson Lee, Hyeji Kim, and Nicholas D. Lane. 2020. BRP-NAS: Prediction-based NAS using GCNs. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31880-4_5"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942147"},{"key":"e_1_3_2_20_2","first-page":"3146","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 3146\u20133154. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/6449f44a102fde848669bdd9eb6b76fa-Abstract.html."},{"key":"e_1_3_2_21_2","volume-title":"5th International Conference on Learning Representations (ICLR\u201917), Conference Track Proceedings","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations (ICLR\u201917), Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=SJU4ayYgl."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169897"},{"key":"e_1_3_2_23_2","volume-title":"9th International Conference on Learning Representations (ICLR\u201921)","author":"Li Chaojian","year":"2021","unstructured":"Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, and Yingyan Lin. 2021. HW-NAS-bench: Hardware-aware neural architecture search benchmark. In 9th International Conference on Learning Representations (ICLR\u201921)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.08734"},{"key":"e_1_3_2_28_2","first-page":"7827","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 (NeurIPS\u201918)","author":"Luo Renqian","year":"2018","unstructured":"Renqian Luo, Fei Tian, Tao Qin, Enhong Chen, and Tie-Yan Liu. 2018. Neural architecture optimization. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 (NeurIPS\u201918), Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicol\u00f2 Cesa-Bianchi, and Roman Garnett (Eds.). 7827\u20137838. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/933670f1ac8ba969f32989c312faba75-Abstract.html."},{"key":"e_1_3_2_29_2","first-page":"778","volume-title":"International Joint Conference on Neural Networks","author":"Massa Vincenzo Di","year":"2006","unstructured":"Vincenzo Di Massa, Gabriele Monfardini, Lorenzo Sarti, Franco Scarselli, Marco Maggini, and Marco Gori. 2006. A comparison between recursive neural networks and graph neural networks. In International Joint Conference on Neural Networks. IEEE, 778\u2013785."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2000.10485979"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268946"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5563-6"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.segan.2016.02.005"},{"key":"e_1_3_2_34_2","first-page":"189","volume-title":"16th European Conference on Computer Vision","author":"Ning Xuefei","year":"2020","unstructured":"Xuefei Ning, Yin Zheng, Tianchen Zhao, Yu Wang, and Huazhong Yang. 2020. A generic graph-based neural architecture encoding scheme for predictor-based NAS. In 16th European Conference on Computer Vision. Springer, 189\u2013204."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/978-3-642-04898-2_324","volume-title":"International Encyclopedia of Statistical Science","author":"Puka Llukan","year":"2011","unstructured":"Llukan Puka. 2011. Kendall\u2019s tau. In International Encyclopedia of Statistical Science, Miodrag Lovric (Ed.). Springer, 713\u2013715."},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41565-020-0655-z"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1109\/CEC45853.2021.9504999","volume-title":"2021 IEEE Congress on Evolutionary Computation","author":"Shi Rui","year":"2021","unstructured":"Rui Shi, Jianping Luo, and Qiqi Liu. 2021. Fast evolutionary neural architecture search based on Bayesian surrogate model. In 2021 IEEE Congress on Evolutionary Computation. 1217\u20131224."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1994.2.3.221"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.00841"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.3390\/e24050656"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.3390\/e24050656"},{"key":"e_1_3_2_44_2","unstructured":"Colin White Arber Zela Binxin Ru Yang Liu and Frank Hutter. 2021. How Powerful Are Performance Predictors in Neural Architecture Search?https:\/\/arxiv.org\/abs\/2104.01177"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525892"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Han Xiao Ziwei Wang Jiwen Lu and Jie Zhou. 2022. Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search. https:\/\/openreview.net\/forum?id=F7nD--1JIC.","DOI":"10.1109\/CVPR52688.2022.01159"},{"key":"e_1_3_2_48_2","article-title":"Resource-aware Pareto-optimal automated machine learning platform","volume":"2011","author":"Yang Yao","year":"2020","unstructured":"Yao Yang, Andrew Nam, Mohamad M. Nasr-Azadani, and Teresa Tung. 2020. Resource-aware Pareto-optimal automated machine learning platform. CoRR abs\/2011.00073 (2020). arXiv:2011.00073https:\/\/arxiv.org\/abs\/2011.00073","journal-title":"CoRR"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.01665"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579853","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3579853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:27Z","timestamp":1750182687000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,15]]},"references-count":48,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,6,30]]}},"alternative-id":["10.1145\/3579853"],"URL":"https:\/\/doi.org\/10.1145\/3579853","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,15]]},"assertion":[{"value":"2022-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-02","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-04-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}