{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:50:12Z","timestamp":1767340212809,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T00:00:00Z","timestamp":1667088000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911-NF-20-1-0167"],"award-info":[{"award-number":["W911-NF-20-1-0167"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1937500, CNS-1909172"],"award-info":[{"award-number":["CCF-1937500, CNS-1909172"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,30]]},"DOI":"10.1145\/3508352.3549379","type":"proceedings-article","created":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T12:10:54Z","timestamp":1671711054000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["All-in-One"],"prefix":"10.1145","author":[{"given":"Yifan","family":"Gong","sequence":"first","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Zhan","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushu","family":"Wu","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Wu","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caiwen","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwen","family":"Jiang","sequence":"additional","affiliation":[{"name":"George Mason University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghai","family":"Qin","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,12,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Courville","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron C. Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. CoRR abs\/1308.3432 (2013). arXiv:1308.3432 http:\/\/arxiv.org\/abs\/1308.3432"},{"key":"e_1_3_2_1_2_1","volume-title":"YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv:2004.10934","author":"Bochkovskiy Alexey","year":"2020","unstructured":"Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv:2004.10934 (2020)."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Learning Representations.","author":"Cai Han","year":"2019","unstructured":"Han Cai, Chuang Gan, Tianzhe Wang, Zhekai Zhang, and Song Han. 2019. Once-for-All: Train One Network and Specialize it for Efficient Deployment. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","volume-title":"Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 119--134","author":"Chin Ting-Wu","year":"2021","unstructured":"Ting-Wu Chin, Ari S Morcos, and Diana Marculescu. 2021. Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 119--134."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Peiyan Dong Siyue Wang et al. 2020. RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition. arXiv:2002.11474 (2020).","DOI":"10.1109\/DAC18072.2020.9218499"},{"key":"e_1_3_2_1_6_1","unstructured":"Yifan Gong Geng Yuan Zheng Zhan Wei Niu Zhengang Li Pu Zhao Yuxuan Cai Sijia Liu Bin Ren Xue Lin et al. 2021. Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration. arXiv preprint arXiv:2111.11581 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3407650"},{"key":"e_1_3_2_1_8_1","volume-title":"DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search. arXiv:2011.02166 [cs.CV]","author":"Guan Yushuo","year":"2020","unstructured":"Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che, Kaigui Bian, Yanzhi Wang, and Jian Tang. 2020. DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search. arXiv:2011.02166 [cs.CV]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00161"},{"key":"e_1_3_2_1_10_1","unstructured":"Yiwen Guo Anbang Yao and Yurong Chen. 2016. Dynamic network surgery for efficient dnns. In NeurIPS. 1379--1387."},{"key":"e_1_3_2_1_11_1","unstructured":"Song Han Jeff Pool et al. 2015. Learning both weights and connections for efficient neural network. In NeurIPS. 1135--1143."},{"key":"e_1_3_2_1_12_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"e_1_3_2_1_14_1","unstructured":"Yang He Ping Liu et al. 2019. Filter pruning via geometric median for deep convolutional neural networks acceleration. In CVPR."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_1_16_1","volume-title":"Yanzhi Wang, and Stratis Ioannidis.","author":"Jian Tong","year":"2021","unstructured":"Tong Jian, Yifan Gong, Zheng Zhan, Runbin Shi, Nasim Soltani, Zifeng Wang, Jennifer G Dy, Kaushik Roy Chowdhury, Yanzhi Wang, and Stratis Ioannidis. 2021. Radio frequency fingerprinting on the edge. IEEE Transactions on Mobile Computing (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"SS-Auto: A single-shot, automatic structured weight pruning framework of DNNs with ultra-high efficiency. arXiv preprint arXiv:2001.08839","author":"Li Zhengang","year":"2020","unstructured":"Zhengang Li, Yifan Gong, Xiaolong Ma, Sijia Liu, Mengshu Sun, Zheng Zhan, Zhenglun Kong, Geng Yuan, and Yanzhi Wang. 2020. SS-Auto: A single-shot, automatic structured weight pruning framework of DNNs with ultra-high efficiency. arXiv preprint arXiv:2001.08839 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Ning Liu Xiaolong Ma et al. 2020. AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates. In AAAI.","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"e_1_3_2_1_19_1","volume-title":"Learning low-precision neural networks without straight-through estimator (ste). arXiv preprint arXiv:1903.01061","author":"Liu Zhi-Gang","year":"2019","unstructured":"Zhi-Gang Liu and Matthew Mattina. 2019. Learning low-precision neural networks without straight-through estimator (ste). arXiv preprint arXiv:1903.01061 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"e_1_3_2_1_21_1","volume-title":"Blk-rew: A unified block-based dnn pruning framework using reweighted regularization method. arXiv preprint arXiv:2001.08357","author":"Ma Xiaolong","year":"2020","unstructured":"Xiaolong Ma, Zhengang Li, Yifan Gong, Tianyun Zhang, Wei Niu, Zheng Zhan, Pu Zhao, Jian Tang, Xue Lin, Bin Ren, et al. 2020. Blk-rew: A unified block-based dnn pruning framework using reweighted regularization method. arXiv preprint arXiv:2001.08357 (2020)."},{"key":"e_1_3_2_1_22_1","unstructured":"Xiaolong Ma Geng Yuan Sheng Lin Caiwen Ding Fuxun Yu Tao Liu Wujie Wen Xiang Chen and Yanzhi Wang. 2020. Tiny but Accurate: A Pruned Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation. In ASP-DAC."},{"key":"e_1_3_2_1_23_1","volume-title":"2PF-PCE: Two-Phase Filter Pruning Based on Conditional Entropy. arXiv preprint arXiv:1809.02220","author":"Min Chuhan","year":"2018","unstructured":"Chuhan Min, Aosen Wang, Yiran Chen, Wenyao Xu, and Xin Chen. 2018. 2PF-PCE: Two-Phase Filter Pruning Based on Conditional Entropy. arXiv preprint arXiv:1809.02220 (2018)."},{"key":"e_1_3_2_1_24_1","volume-title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning. arXiv preprint arXiv:2001.00138","author":"Niu Wei","year":"2020","unstructured":"Wei Niu, Xiaolong Ma, Sheng Lin, Shihao Wang, Xuehai Qian, Xue Lin, Yanzhi Wang, and Bin Ren. 2020. PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning. arXiv preprint arXiv:2001.00138 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time. arXiv preprint arXiv:2110.04252","author":"Nunez Elvis","year":"2021","unstructured":"Elvis Nunez, Maxwell Horton, Anish Prabhu, Anurag Ranjan, Ali Farhadi, and Mohammad Rastegari. 2021. LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time. arXiv preprint arXiv:2110.04252 (2021)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586295"},{"key":"e_1_3_2_1_27_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_28_1","unstructured":"Wei Wen Chunpeng Wu et al. 2016. Learning structured sparsity in deep neural networks. In NeurIPS. 2074--2082."},{"key":"e_1_3_2_1_29_1","volume-title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution. arXiv preprint arXiv:2207.12577","author":"Wu Yushu","year":"2022","unstructured":"Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, and Yanzhi Wang. 2022. Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution. arXiv preprint arXiv:2207.12577 (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Understanding straight-through estimator in training activation quantized neural nets. arXiv preprint arXiv:1903.05662","author":"Yin Penghang","year":"2019","unstructured":"Penghang Yin, Jiancheng Lyu, Shuai Zhang, Stanley Osher, Yingyong Qi, and Jack Xin. 2019. Understanding straight-through estimator in training activation quantized neural nets. arXiv preprint arXiv:1903.05662 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"e_1_3_2_1_32_1","volume-title":"Slimmable neural networks. arXiv preprint arXiv:1812.08928","author":"Yu Jiahui","year":"2018","unstructured":"Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, and Thomas Huang. 2018. Slimmable neural networks. arXiv preprint arXiv:1812.08928 (2018)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.15"},{"key":"e_1_3_2_1_34_1","first-page":"20838","article-title":"2021. 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_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00478"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586152"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Tianyun Zhang Shaokai Ye et al. 2018. Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers. ECCV (2018).","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"e_1_3_2_1_38_1","volume-title":"Adam-admm: A unified, systematic framework of structured weight pruning for dnns. arXiv preprint arXiv:1807.11091","author":"Zhang Tianyun","year":"2018","unstructured":"Tianyun Zhang, Kaiqi Zhang, Shaokai Ye, Jian Tang, Wujie Wen, Xue Lin, Makan Fardad, and Yanzhi Wang. 2018. Adam-admm: A unified, systematic framework of structured weight pruning for dnns. arXiv preprint arXiv:1807.11091 (2018)."},{"key":"e_1_3_2_1_39_1","unstructured":"Chenglong Zhao Bingbing Ni Jian Zhang Qiwei Zhao Wenjun Zhang and Qi Tian. 2019. Variational Convolutional Neural Network Pruning. In CVPR. 2780--2789."},{"key":"e_1_3_2_1_40_1","unstructured":"Xiaotian Zhu Wengang Zhou and Houqiang Li. 2018. Improving Deep Neural Network Sparsity through Decorrelation Regularization. In IJCAI."},{"key":"e_1_3_2_1_41_1","unstructured":"Zhuangwei Zhuang Mingkui Tan et al. 2018. Discrimination-aware channel pruning for deep neural networks. In NeurIPS. 875--886."}],"event":{"name":"ICCAD '22: IEEE\/ACM International Conference on Computer-Aided Design","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-EDS Electronic Devices Society","IEEE CAS","IEEE CEDA"],"location":"San Diego California","acronym":"ICCAD '22"},"container-title":["Proceedings of the 41st IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3508352.3549379","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3508352.3549379","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3508352.3549379","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:23Z","timestamp":1750188623000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3508352.3549379"}},"subtitle":["A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management"],"short-title":[],"issued":{"date-parts":[[2022,10,30]]},"references-count":41,"alternative-id":["10.1145\/3508352.3549379","10.1145\/3508352"],"URL":"https:\/\/doi.org\/10.1145\/3508352.3549379","relation":{},"subject":[],"published":{"date-parts":[[2022,10,30]]},"assertion":[{"value":"2022-12-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}