{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T02:33:40Z","timestamp":1778726020125,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"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":[[2024,6,12]]},"DOI":"10.1145\/3649476.3658699","type":"proceedings-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T12:29:41Z","timestamp":1718022581000},"page":"694-699","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Resource-Aware Saliency-Guided Differentiable Pruning for Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1150-3903","authenticated-orcid":false,"given":"Uttej","family":"Kallakuri","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, Johns Hopkins University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3945-0116","authenticated-orcid":false,"given":"Edward","family":"Humes","sequence":"additional","affiliation":[{"name":"Computer Science, University of Maryland, Baltimore County, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-2124","authenticated-orcid":false,"given":"Tinoosh","family":"Mohsenin","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Johns Hopkins University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"20852","article-title":"The generalization-stability tradeoff in neural network pruning","volume":"33","author":"Bartoldson Brian","year":"2020","unstructured":"Brian Bartoldson, Ari Morcos, Adrian Barbu, and Gordon Erlebacher. 2020. The generalization-stability tradeoff in neural network pruning. Advances in Neural Information Processing Systems 33 (2020), 20852\u201320864.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_2_1","volume-title":"Directional pruning of deep neural networks. Advances in neural information processing systems 33","author":"Chao Shih-Kang","year":"2020","unstructured":"Shih-Kang Chao, Zhanyu Wang, Yue Xing, and Guang Cheng. 2020. Directional pruning of deep neural networks. Advances in neural information processing systems 33 (2020), 13986\u201313998."},{"key":"e_1_3_2_1_3_1","volume-title":"A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations. arXiv preprint arXiv:2308.06767","author":"Cheng Hongrong","year":"2023","unstructured":"Hongrong Cheng, Miao Zhang, and Javen\u00a0Qinfeng Shi. 2023. A survey on deep neural network pruning-taxonomy, comparison, analysis, and recommendations. arXiv preprint arXiv:2308.06767 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Angel-eye: A complete design flow for mapping CNN onto embedded FPGA","author":"Guo Kaiyuan","year":"2017","unstructured":"Kaiyuan Guo, Lingzhi Sui, Jiantao Qiu, Jincheng Yu, Junbin Wang, Song Yao, Song Han, Yu Wang, and Huazhong Yang. 2017. Angel-eye: A complete design flow for mapping CNN onto embedded FPGA. IEEE transactions on computer-aided design of integrated circuits and systems 37, 1 (2017), 35\u201347."},{"key":"e_1_3_2_1_5_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William\u00a0J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317873"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2021.3111431"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3110250"},{"key":"e_1_3_2_1_10_1","volume-title":"Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans\u00a0Peter Graf. 2016. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710 (2016)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569468"},{"key":"e_1_3_2_1_13_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2019.00013"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3129415"},{"key":"e_1_3_2_1_16_1","volume-title":"Reg-TuneV2: Hardware-Aware and Multi-Objective Regression-Based Fine-Tuning Approach for DNNs on Embedded Platforms","author":"Mazumder Arnab\u00a0Neelim","year":"2023","unstructured":"Arnab\u00a0Neelim Mazumder and Tinoosh Mohsenin. 2023. Reg-TuneV2: Hardware-Aware and Multi-Objective Regression-Based Fine-Tuning Approach for DNNs on Embedded Platforms. IEEE Micro (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"TinyM2Net-V2: A Compact Low Power Software Hardware Architecture for Multimodal Deep Neural Networks. ACM Transactions on Embedded Computing Systems","author":"Hasib-Al","year":"2023","unstructured":"Hasib-Al Rashid 2023. TinyM2Net-V2: A Compact Low Power Software Hardware Architecture for Multimodal Deep Neural Networks. ACM Transactions on Embedded Computing Systems (2023)."},{"key":"e_1_3_2_1_18_1","unstructured":"James\u00a0K. Reed Zachary DeVito Horace He Ansley Ussery and Jason Ansel. 2022. Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python. arxiv:2112.08429\u00a0[cs.LG]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682791"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_21_1","volume-title":"Learning structured sparsity in deep neural networks. Advances in neural information processing systems 29","author":"Wen Wei","year":"2016","unstructured":"Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2016. Learning structured sparsity in deep neural networks. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.032"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"},{"key":"e_1_3_2_1_24_1","volume-title":"StructADMM: A systematic, high-efficiency framework of structured weight pruning for DNNs. arXiv preprint arXiv:1807.11091","author":"Zhang Tianyun","year":"2018","unstructured":"Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Xiaolong Ma, Ning Liu, Linfeng Zhang, Jian Tang, Kaisheng Ma, Xue Lin, Makan Fardad, 2018. StructADMM: A systematic, high-efficiency framework of structured weight pruning for DNNs. arXiv preprint arXiv:1807.11091 (2018)."},{"key":"e_1_3_2_1_25_1","volume-title":"Hello edge: Keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128","author":"Zhang Yundong","year":"2017","unstructured":"Yundong Zhang, Naveen Suda, Liangzhen Lai, and Vikas Chandra. 2017. Hello edge: Keyword spotting on microcontrollers. arXiv preprint arXiv:1711.07128 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)."}],"event":{"name":"GLSVLSI '24: Great Lakes Symposium on VLSI 2024","location":"Clearwater FL USA","acronym":"GLSVLSI '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658699","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:31:05Z","timestamp":1755829865000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":26,"alternative-id":["10.1145\/3649476.3658699","10.1145\/3649476"],"URL":"https:\/\/doi.org\/10.1145\/3649476.3658699","relation":{},"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"2024-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}