{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T15:10:07Z","timestamp":1751037007936,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735193","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:00:26Z","timestamp":1751032826000},"page":"667-672","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CNN Model Optimization Using a Hybrid Approach of Genetic Algorithm-based Pruning and Retraining with Knowledge Distillation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7229-0726","authenticated-orcid":false,"given":"Kuan-Ling","family":"Chou","sequence":"first","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8593-6567","authenticated-orcid":false,"given":"Cheng-Lung","family":"Wang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-800X","authenticated-orcid":false,"given":"Yung-Chih","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University of Science and Technology, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5042-5062","authenticated-orcid":false,"given":"Wuqian","family":"Tang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5297-9420","authenticated-orcid":false,"given":"Yi-Ting","family":"Li","sequence":"additional","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0717-6466","authenticated-orcid":false,"given":"Shih-Chieh","family":"Chang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-214X","authenticated-orcid":false,"given":"Chun-Yao","family":"Wang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University, Hsinchu, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Pattern recognition and machine learning","author":"Bishop Christopher\u00a0M","year":"2006","unstructured":"Christopher\u00a0M Bishop and Nasser\u00a0M Nasrabadi. 2006. Pattern recognition and machine learning. Vol.\u00a04. Springer."},{"key":"e_1_3_3_1_3_2","unstructured":"Davis Blalock Jose\u00a0Javier Gonzalez\u00a0Ortiz Jonathan Frankle and John Guttag. 2020. What is the state of neural network pruning? Proc. machine learning and systems 2 (2020) 129\u2013146."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.406"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Hanjing Cheng Zidong Wang Lifeng Ma Xiaohui Liu and Zhihui Wei. 2021. Multi-task pruning via filter index sharing: A many-objective optimization approach. Cognitive Computation 13 4 (2021) 1070\u20131084.","DOI":"10.1007\/s12559-021-09894-x"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Hanjing Cheng Zidong Wang Lifeng Ma Zhihui Wei Fawaz\u00a0E Alsaadi and Xiaohui Liu. 2023. Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach. Complex & Intelligent Systems 9 5 (2023) 5611\u20135624.","DOI":"10.1007\/s40747-023-01022-6"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/AAI28115679"},{"key":"e_1_3_3_1_9_2","volume-title":"Proc. NeurIPS","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William\u00a0J. Dally. 2015. Learning both Weights and Connections for Efficient Neural Networks. In Proc. NeurIPS."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00895"},{"key":"e_1_3_3_1_12_2","unstructured":"Yang He and Lingao Xiao. 2023. Structured pruning for deep convolutional neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence (2023)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_3_1_14_2","volume-title":"Proc. NeurIPS","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. In Proc. NeurIPS."},{"key":"e_1_3_3_1_15_2","first-page":"10","volume-title":"Proc. ISSCC","author":"Horowitz Mark","year":"2014","unstructured":"Mark Horowitz. 2014. 1.1 computing\u2019s energy problem (and what we can do about it). In Proc. ISSCC. 10\u201314."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITSA60681.2024.10546442"},{"key":"e_1_3_3_1_17_2","unstructured":"Y. Idelbayev. 2021. Proper ResNet implementation for CIFAR10\/CIFAR100 in PyTorch. https:\/\/github.com\/akamaster\/pytorch_resnet_cifar10."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Onur K\u00f6ksoy and Tankut Yalcinoz. 2008. Robust design using Pareto type optimization: a genetic algorithm with arithmetic crossover. Computers & Industrial Engineering 55 1 (2008) 208\u2013218.","DOI":"10.1016\/j.cie.2007.11.019"},{"key":"e_1_3_3_1_20_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Solomon Kullback and Richard\u00a0A Leibler. 1951. On information and sufficiency. The Annals of Mathematical Statistics 22 1 (1951) 79\u201386.","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Aakash Kumar Ali\u00a0Muhammad Shaikh Yun Li Hazrat Bilal and Baoqun Yin. 2021. Pruning filters with L1-norm and capped L1-norm for CNN compression. Applied Intelligence 51 (2021) 1152\u20131160.","DOI":"10.1007\/s10489-020-01894-y"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun Leon Bottou Yoshua Bengio and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. the IEEE 86 11 (1998) 2278\u20132324.","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567890"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_3_3_1_26_2","unstructured":"Zhuang Liu Mingjie Sun Tinghui Zhou Gao Huang and Trevor Darrell. 2018. Rethinking the value of network pruning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1810.05270 (2018)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"e_1_3_3_1_28_2","unstructured":"Microsoft Corporation. 2024. HoloLens. https:\/\/www.microsoft.com\/en-us\/hololens."},{"key":"e_1_3_3_1_29_2","unstructured":"Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1611.06440 (2016)."},{"key":"e_1_3_3_1_30_2","volume-title":"Proc. NeurIPS","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proc. NeurIPS."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Svetlana Pavlitska Oliver Bagge Federico Peccia Toghrul Mammadov and J\u00a0Marius Z\u00f6llner. 2024. Iterative Filter Pruning for Concatenation-based CNN Architectures. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.03715 (2024).","DOI":"10.1109\/IJCNN60899.2024.10650334"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Russell Reed. 1993. Pruning algorithms-a survey. IEEE transactions on Neural Networks 4 5 (1993) 740\u2013747.","DOI":"10.1109\/72.248452"},{"key":"e_1_3_3_1_33_2","volume-title":"Proc. ICLR","author":"Renda Alex","year":"2020","unstructured":"Alex Renda, Jonathan Frankle, and Michael Carbin. 2020. Comparing Rewinding and Fine-tuning in Neural Network Pruning. In Proc. ICLR."},{"key":"e_1_3_3_1_34_2","volume-title":"Proc. ICGA","author":"Syswerda Gilbert","year":"1989","unstructured":"Gilbert Syswerda et\u00a0al. 1989. Uniform crossover in genetic algorithms.. In Proc. ICGA, Vol.\u00a03."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC62300.2024.10737843"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Yifan Zhang Congqi Cao Jian Cheng and Hanqing Lu. 2018. EgoGesture: A new dataset and benchmark for egocentric hand gesture recognition. IEEE Transactions on Multimedia 20 5 (2018) 1038\u20131050.","DOI":"10.1109\/TMM.2018.2808769"},{"key":"e_1_3_3_1_39_2","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.01878 (2017)."}],"event":{"name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"New Orleans LA USA","acronym":"GLSVLSI '25"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:36:58Z","timestamp":1751035018000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":38,"alternative-id":["10.1145\/3716368.3735193","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735193","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}