{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:55:10Z","timestamp":1781794510073,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3787109.3816377","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"200-207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PRISM: Pruning via Rectified-gradient Importance and Saliency Mapping \u2014 making models sparse for execution on edge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9581-8348","authenticated-orcid":false,"given":"Zuxiong","family":"Tan","sequence":"first","affiliation":[{"name":"University of California, Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6075-0880","authenticated-orcid":false,"given":"Ali","family":"Karkehabadi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of California, Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-4699","authenticated-orcid":false,"given":"Houman","family":"Homayoun","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1724-3503","authenticated-orcid":false,"given":"Tooraj","family":"Nikoubin","sequence":"additional","affiliation":[{"name":"ECE, University of Texas at Dallas, Dallas, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4052-8075","authenticated-orcid":false,"given":"Avesta","family":"Sasan","sequence":"additional","affiliation":[{"name":"University of California, Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01203"},{"key":"e_1_3_3_1_3_2","volume-title":"AAAI","author":"Castells Thibault","year":"2023","unstructured":"Thibault Castells and Seul-Ki Yeom. 2023. Automatic neural network pruning that efficiently preserves the model accuracy. In AAAI."},{"key":"e_1_3_3_1_4_2","volume-title":"NeurIPS","author":"Chen Tianlong","year":"2021","unstructured":"Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, and Zhangyang Wang. 2021. Chasing Sparsity in Vision Transformers: An End-to-End Exploration. In NeurIPS."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Zailong Chen Chubo Liu Wangdong Yang Kenli Li and Keqin Li. 2022. LAP: Latency-aware automated pruning with dynamic-based filter selection. Neural Networks 152 (2022) 407\u2013418.","DOI":"10.1016\/j.neunet.2022.05.002"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Zhuangzhi Chen Jingyang Xiang Yao Lu Qi Xuan Zhen Wang Guanrong Chen and Xiaoniu Yang. 2024. RGP: Neural network pruning through regular graph with edges swapping. IEEE Transactions on Neural Networks and Learning Systems 35 10 (2024) 14671\u201314683.","DOI":"10.1109\/TNNLS.2023.3280899"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00447"},{"key":"e_1_3_3_1_10_2","volume-title":"Asian Conference on Computer Vision","author":"Duan Yuanzhi","year":"2022","unstructured":"Yuanzhi Duan, Yue Zhou, Peng He, Qiang Liu, Shukai Duan, and Xiaofang Hu. 2022. Network pruning via feature shift minimization. In Asian Conference on Computer Vision."},{"key":"e_1_3_3_1_11_2","volume-title":"ECCV","author":"Fang Gongfan","year":"2024","unstructured":"Gongfan Fang, Xinyin Ma, Michael\u00a0Bi Mi, and Xinchao Wang. 2024. Isomorphic Pruning for Vision Models. In ECCV."},{"key":"e_1_3_3_1_12_2","volume-title":"ICLR","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. 2019. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. In ICLR. https:\/\/openreview.net\/forum?id=rye4g3AqFm"},{"key":"e_1_3_3_1_13_2","volume-title":"Int. Conf. Mach. Learn.","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot. In Int. Conf. Mach. Learn."},{"key":"e_1_3_3_1_14_2","unstructured":"Trevor Gale. 2020. The Future of Sparsity in Deep Neural Networks. SIGARCH Computer Architecture Today Blog (2020). https:\/\/www.sigarch.org\/the-future-of-sparsity-in-deep-neural-networks\/"},{"key":"e_1_3_3_1_15_2","unstructured":"Qingbei Guo Xiao-Jun Wu Josef Kittler and Zhiquan Feng. 2021. Weak sub-network pruning for strong and efficient neural networks. Neural Networks (2021)."},{"key":"e_1_3_3_1_16_2","first-page":"17458","volume-title":"ICCV","author":"Guo Song","year":"2023","unstructured":"Song Guo, Lei Zhang, Xiawu Zheng, Yan Wang, Yuchao Li, Fei Chao, Chenglin Wu, Shengchuan Zhang, and Rongrong Ji. 2023. Automatic network pruning via Hilbert\u2013Schmidt independence criterion lasso under information bottleneck principle. In ICCV. 17458\u201317469."},{"key":"e_1_3_3_1_17_2","first-page":"1135","volume-title":"NeurIPS","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural networks. In NeurIPS , Vol.\u00a028. 1135\u20131143."},{"key":"e_1_3_3_1_18_2","first-page":"164","volume-title":"NeurIPS","author":"Hassibi Babak","year":"1993","unstructured":"Babak Hassibi and David\u00a0G. Stork. 1993. Second-order derivatives for network pruning: Optimal Brain Surgeon. In NeurIPS , Vol.\u00a05. 164\u2013171."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_20_2","unstructured":"Torsten Hoefler Dan Alistarh Tal Ben-Nun Nikoli Dryden and Alexandra Peste. 2021. Sparsity in Deep Learning: Pruning and Growth for Efficient Inference and Training in Neural Networks. Journal of Machine Learning Research 22 (2021) 1\u2013124."},{"key":"e_1_3_3_1_21_2","unstructured":"Yuezhou Hu Jun Zhu and Jianfei Chen. 2024. S-STE: Continuous pruning function for efficient 2:4 sparse pre-training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.09099 (2024)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00799"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCAS61159.2024.10539909"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST63249.2024.10805345"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00510"},{"key":"e_1_3_3_1_26_2","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto."},{"key":"e_1_3_3_1_27_2","first-page":"598","volume-title":"NeurIPS","author":"LeCun Yann","year":"1990","unstructured":"Yann LeCun, John\u00a0S. Denker, and Sara\u00a0A. Solla. 1990. Optimal Brain Damage. In NeurIPS , Vol.\u00a02. 598\u2013605."},{"key":"e_1_3_3_1_28_2","volume-title":"ICLR","author":"Lee Namhoon","year":"2019","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip\u00a0HS Torr. 2019. SNIP: Single-shot Network Pruning Based on Connection Sensitivity. In ICLR."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Jiang Li Haijian Shao Shengjie Zhai Yingtao Jiang and Xing Deng. 2023. A graphical approach for filter pruning by exploring the similarity relation between feature maps. Pattern Recognition Letters 166 (2023) 69\u201375.","DOI":"10.1016\/j.patrec.2022.12.028"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00637"},{"key":"e_1_3_3_1_31_2","unstructured":"Mingbao Lin Liujuan Cao Yuxin Zhang Ling Shao Chia-Wen Lin and Rongrong Ji. 2022. Pruning networks with cross-layer ranking and k-reciprocal nearest filters. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/94"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00365"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"e_1_3_3_1_36_2","unstructured":"Jian-Hao Luo and Jianxin Wu. 2020. AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference. Pattern Recognition (2020). Preprint submitted to Pattern Recognition."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.241"},{"key":"e_1_3_3_1_38_2","volume-title":"AAAI","author":"Pan Bowen","year":"2023","unstructured":"Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, and Aude Oliva. 2023. GOHSP: A Unified Framework of Graph and Optimization-Based Heterogeneous Structured Pruning for Vision Transformers. In AAAI."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Van\u00a0Tien Pham Yassine Zniyed and Thanh\u00a0Phuong Nguyen. 2024. Efficient tensor decomposition-based filter pruning. Neural Networks 178 (2024) 106393.","DOI":"10.1016\/j.neunet.2024.106393"},{"key":"e_1_3_3_1_41_2","unstructured":"Jeff Pool. 2020. Accelerating sparsity in the NVIDIA Ampere architecture. GPU Technology Conference Presentation. NVIDIA GTC 2020."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_1_43_2","unstructured":"Gil Shomron and Uri Weiser. 2020. Post\u2010training BatchNorm recalibration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.05625 (2020)."},{"key":"e_1_3_3_1_44_2","volume-title":"Int. Conf. Mach. Learn.","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Patrick Greenside, and Anshul Kundaje. 2017. Learning Important Features through Propagating Activation Differences. In Int. Conf. Mach. Learn."},{"key":"e_1_3_3_1_45_2","volume-title":"ICLR","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In ICLR. Workshop Track."},{"key":"e_1_3_3_1_46_2","volume-title":"ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In ICLR."},{"key":"e_1_3_3_1_47_2","volume-title":"Int. Conf. Mach. Learn.","author":"Smilkov Daniel","year":"2017","unstructured":"Daniel Smilkov, Nalini Thorat, Been Kim, Fernanda Vi\u00e9gas, and Martin Wattenberg. 2017. SmoothGrad: Removing Noise by Adding Noise. In Int. Conf. Mach. Learn.Workshop on Visualization for Deep Learning."},{"key":"e_1_3_3_1_48_2","unstructured":"Zhuoran Song Yihong Xu Zhezhi He Li Jiang Naifeng Jing and Xiaoyao Liang. 2022. CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.04570 (2022)."},{"key":"e_1_3_3_1_49_2","volume-title":"NeurIPS","author":"Sui Yang","year":"2021","unstructured":"Yang Sui, Miao Yin, Yi Xie, Huy Phan, Saman Zonouz, and Bo Yuan. 2021. CHIP: Channel independence-based pruning for compact neural networks. In NeurIPS."},{"key":"e_1_3_3_1_50_2","volume-title":"ICLR","author":"Sun Mingjie","year":"2024","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and J.\u00a0Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. In ICLR."},{"key":"e_1_3_3_1_51_2","volume-title":"Asian Conference on Computer Vision","author":"Sun Qiming","year":"2022","unstructured":"Qiming Sun, Shan Cao, and Zhixiang Chen. 2022. Automatic Pruning Rate Search. In Asian Conference on Computer Vision."},{"key":"e_1_3_3_1_52_2","volume-title":"NeurIPS","author":"Tanaka Hidenori","year":"2020","unstructured":"Hidenori Tanaka, Daniel Kunin, Daniel Yamins, and Surya Ganguli. 2020. Pruning neural networks without any data by iteratively conserving synaptic flow. In NeurIPS , Vol.\u00a033."},{"key":"e_1_3_3_1_53_2","volume-title":"NeurIPS","author":"Tang Yehui","year":"2020","unstructured":"Yehui Tang, Yunhe Wang, Yixing Xu, Dacheng Tao, Chunjing Xu, Chao Xu, and Chang Xu. 2020. SCOP: Scientific control for reliable neural network pruning. In NeurIPS."},{"key":"e_1_3_3_1_54_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training Data\u2013Efficient Image Transformers & Distillation Through Attention. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_1_55_2","volume-title":"ICLR","author":"Wang Chaoqi","year":"2020","unstructured":"Chaoqi Wang, Guodong Zhang, and Roger Grosse. 2020. Picking Winning Tickets Before Training by Preserving Gradient Flow. In ICLR."},{"key":"e_1_3_3_1_56_2","volume-title":"ICLR","author":"Wang Huan","year":"2023","unstructured":"Huan Wang and Yun Fu. 2023. Trainability preserving neural pruning. In ICLR."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"Zidu Wang Xuexin Liu Long Huang Yunqing Chen Yufei Zhang Zhikang Lin and Rui Wang. 2022. QSFM: Model pruning based on quantified similarity between feature maps for AI on edge. IEEE Internet of Things Journal 9 23 (2022) 24506\u201324515.","DOI":"10.1109\/JIOT.2022.3190873"},{"key":"e_1_3_3_1_58_2","volume-title":"NeurIPS","author":"Wang Zhenyu","year":"2022","unstructured":"Zhenyu Wang, Hao Luo, Pichao Wang, Feng Ding, Fan Wang, and Hao Li. 2022. Vision Transformer Compression with Low-Frequency Components. In NeurIPS."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01500"},{"key":"e_1_3_3_1_60_2","volume-title":"Int. Conf. Mach. Learn.","author":"Yang Chenyi","year":"2025","unstructured":"Chenyi Yang, Wenjie Nie, Yuxin Zhang, Yuhang Wu, Xiawu Zheng, Guannan Jiang, and Rongrong Ji. 2025. Block-Aware Mask Evolution for Efficient N:M Sparse Training. In Int. Conf. Mach. Learn."},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"crossref","unstructured":"Huoxiang Yang Yongsheng Liang Wei Liu and Fanyang Meng. 2023. Filter pruning via attention consistency on feature maps. Applied Sciences 13 3 (2023) 1964.","DOI":"10.3390\/app13031964"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20222"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"e_1_3_3_1_65_2","volume-title":"ICLR","author":"Yu Shixing","year":"2022","unstructured":"Shixing Yu, Tianlong Chen, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen Yang, Ji Liu, and Zhangyang Wang. 2022. Unified Visual Transformer Compression. In ICLR."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Shuo Zhang Qiang Ni and Jungong Han. 2023. Filter pruning with uniqueness mechanism in the frequency domain for efficient neural networks. Neurocomputing 530 (2023) 116\u2013124.","DOI":"10.1016\/j.neucom.2023.02.004"},{"key":"e_1_3_3_1_67_2","unstructured":"Yuxin Zhang Mingbao Lin Chia-Wen Lin Jie Chen Feiyue Huang Yongjian Wu Yonghong Tian and Rongrong Ji. 2022. Carrying out CNN channel pruning in a white box. IEEE Transactions on Neural Networks and Learning Systems (2022). also available as arXiv:https:\/\/arXiv.org\/abs\/2104.11883."},{"key":"e_1_3_3_1_68_2","volume-title":"NeurIPS","author":"Zhang Yuxin","year":"2022","unstructured":"Yuxin Zhang, Mingbao Lin, Zhihang Lin, Yiting Luo, Ke Li, Fei Chao, Yongjian Wu, and Rongrong Ji. 2022. Learning best combination for efficient N:M sparsity. In NeurIPS."},{"key":"e_1_3_3_1_69_2","volume-title":"International Conference on Machine Learning","author":"Zhang Yuxin","year":"2023","unstructured":"Yuxin Zhang, Yiting Luo, Mingbao Lin, Yunshan Zhong, Jingjing Xie, Fei Chao, and Rongrong Ji. 2023. Bi-directional masks for efficient N:M sparse training. In International Conference on Machine Learning."},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"crossref","unstructured":"Chenghui Zhen Weiwei Zhang Jian Mo Ming Ji Hongbo Zhou and Jianqing Zhu. 2023. RASP: Regularization-based amplitude saliency pruning. Neural Networks 168 (2023) 1\u201313.","DOI":"10.1016\/j.neunet.2023.09.002"},{"key":"e_1_3_3_1_71_2","volume-title":"NeurIPS","author":"Zheng Chuanyang","year":"2022","unstructured":"Chuanyang Zheng, Zheyang Li, Kai Zhang, Zhi Yang, Wenming Tan, Jun Xiao, Ye Ren, and Shiliang Pu. 2022. SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization. In NeurIPS."},{"key":"e_1_3_3_1_72_2","volume-title":"ICLR","author":"Zhou Aojun","year":"2021","unstructured":"Aojun Zhou, Yukun Ma, Junnan Zhu, Jianbo Liu, Zhijie Zhang, Kun Yuan, Wenxiu Sun, and Hongsheng Li. 2021. Learning N:M Fine-grained Structured Sparse Neural Networks from Scratch. In ICLR."},{"key":"e_1_3_3_1_73_2","unstructured":"Xuan Zu Yun Li and Baoqun Yin. 2023. Consecutive layer collaborative filter similarity for differentiable neural network pruning. Neurocomputing (2023)."}],"event":{"name":"GLSVLSI '26: Great Lakes Symposium on VLSI 2026","location":"Canandaigua , NY , USA","acronym":"GLSVLSI '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2026"],"original-title":[],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:28:39Z","timestamp":1781792919000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3816377"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":72,"alternative-id":["10.1145\/3787109.3816377","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3816377","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}