{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:00Z","timestamp":1765544940587,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611741","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9003-9011","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Finding Efficient Pruned Network via Refined Gradients for Pruned Weights"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1334-4649","authenticated-orcid":false,"given":"Jangho","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science, Kookmin University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-2260","authenticated-orcid":false,"given":"Jayeon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5436-5801","authenticated-orcid":false,"given":"Yeji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-1607","authenticated-orcid":false,"given":"KiYoon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-0327","authenticated-orcid":false,"given":"Nojun","family":"Kwak","sequence":"additional","affiliation":[{"name":"Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_2_1","volume-title":"Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840","author":"Dettmers Tim","year":"2019","unstructured":"Tim Dettmers and Luke Zettlemoyer. 2019. Sparse networks from scratch: Faster training without losing performance. arXiv preprint arXiv:1907.04840 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Machine Learning. PMLR, 2943--2952","author":"Evci Utku","year":"2020","unstructured":"Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, and Erich Elsen. 2020. Rigging the lottery: Making all tickets winners. In International Conference on Machine Learning. PMLR, 2943--2952."},{"key":"e_1_3_2_1_5_1","first-page":"1379","article-title":"Dynamic Network Surgery for Efficient DNNs","volume":"29","author":"Guo Yiwen","year":"2016","unstructured":"Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic Network Surgery for Efficient DNNs. Advances in Neural Information Processing Systems 29 (2016), 1379--1387.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","volume-title":"Learning both weights and connections for efficient neural networks. Advances in Neural Information Processing Systems","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William J Dally. 2015. Learning both weights and connections for efficient neural networks. Advances in Neural Information Processing Systems (2015)."},{"key":"e_1_3_2_1_7_1","unstructured":"Babak Hassibi and David G Stork. 1993. Second order derivatives for network pruning: Optimal brain surgeon. Morgan Kaufmann."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_12_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Kim Jangho","year":"2018","unstructured":"Jangho Kim, Seonguk Park, and Nojun Kwak. 2018. Paraphrasing Complex Network: Network Compression via Factor Transfer. In Advances in Neural Information Processing Systems, Vol. 31."},{"key":"e_1_3_2_1_14_1","volume-title":"Position-based scaled gradient for model quantization and pruning. Advances in neural information processing systems 33","author":"Kim Jangho","year":"2020","unstructured":"Jangho Kim, KiYoon Yoo, and Nojun Kwak. 2020. Position-based scaled gradient for model quantization and pruning. Advances in neural information processing systems 33 (2020), 20415--20426."},{"key":"e_1_3_2_1_15_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_16_1","unstructured":"Yann LeCun John S Denker and Sara A Solla. 1990. Optimal brain damage. In Advances in neural information processing systems. 598--605."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations","author":"Li Hao","year":"2017","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning filters for efficient convnets. International Conference on Learning Representations (2017)."},{"key":"e_1_3_2_1_18_1","volume-title":"InternationalConference on Learning Representations","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Sebastian U Stich, Luis Barba, Daniil Dmitriev, and Martin Jaggi. 2020. Dynamic model pruning with feedback. InternationalConference on Learning Representations (2020)."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Learning Representations","author":"Liu Zhuang","year":"2019","unstructured":"Zhuang Liu, Mingjie Sun, Tinghui Zhou, Gao Huang, and Trevor Darrell. 2019. Rethinking the value of network pruning. International Conference on Learning Representations (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications 9, 1","author":"Mocanu Decebal Constantin","year":"2018","unstructured":"Decebal Constantin Mocanu, Elena Mocanu, Peter Stone, Phuong H Nguyen, Madeleine Gibescu, and Antonio Liotta. 2018. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications 9, 1 (2018), 1--12."},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 4646--4655","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In International Conference on Machine Learning. PMLR, 4646--4655."},{"key":"e_1_3_2_1_22_1","first-page":"8557","article-title":"Ac\/dc: Alternating compressed\/decompressed training of deep neural networks","volume":"34","author":"Peste Alexandra","year":"2021","unstructured":"Alexandra Peste, Eugenia Iofinova, Adrian Vladu, and Dan Alistarh. 2021. Ac\/dc: Alternating compressed\/decompressed training of deep neural networks. Advances in Neural Information Processing Systems 34 (2021), 8557--8570.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations","author":"Renda Alex","year":"2020","unstructured":"Alex Renda, Jonathan Frankle, and Michael Carbin. 2020. Comparing rewinding and fine-tuning in neural network pruning. International Conference on Learning Representations (2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_25_1","first-page":"18098","article-title":"Woodfisher: Efficient second-order approximation for neural network compression","volume":"33","author":"Singh Sidak Pal","year":"2020","unstructured":"Sidak Pal Singh and Dan Alistarh. 2020. Woodfisher: Efficient second-order approximation for neural network compression. Advances in Neural Information Processing Systems 33 (2020), 18098--18109.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_27_1","volume-title":"Autoprune: Automatic network pruning by regularizing auxiliary parameters. Advances in Neural Information Processing Systems 32 (NeurIPS 2019) 32","author":"Xiao Xia","year":"2019","unstructured":"Xia Xiao and Zigeng Wang. 2019. Autoprune: Automatic network pruning by regularizing auxiliary parameters. Advances in Neural Information Processing Systems 32 (NeurIPS 2019) 32 (2019)."},{"key":"e_1_3_2_1_28_1","first-page":"20838","article-title":"Mest: Accurate and fast memory-economic sparse training framework on the edge","volume":"34","author":"Yuan Geng","year":"2021","unstructured":"Geng Yuan, Xiaolong Ma, Wei Niu, Zhengang Li, Zhenglun Kong, Ning Liu, Yifan Gong, Zheng Zhan, Chaoyang He, Qing Jin, et al. 2021. Mest: Accurate and fast memory-economic sparse training framework on the edge. Advances in Neural Information Processing Systems 34 (2021), 20838--20850.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_2_1_30_1","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878","author":"Zhu Michael","year":"2017","unstructured":"Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878 (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Learning Representations","author":"Zimmer Max","year":"2023","unstructured":"Max Zimmer, Christoph Spiegel, and Sebastian Pokutta. 2023. How I Learned to Stop Worrying and Love Retraining. International Conference on Learning Representations (2023)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:09:54Z","timestamp":1755821394000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":31,"alternative-id":["10.1145\/3581783.3611741","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611741","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}