{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T13:40:07Z","timestamp":1750858807637,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,18]]},"DOI":"10.1145\/3703323.3703339","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T12:03:28Z","timestamp":1750853008000},"page":"102-106","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Application Specific Compression of Deep Learning Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6002-1767","authenticated-orcid":false,"given":"Rohit Raj","family":"Rai","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, IIT Guwahati, Guwahati, Assam, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7736-274X","authenticated-orcid":false,"given":"Angana","family":"Borah","sequence":"additional","affiliation":[{"name":"University of Michigan Ann Arbor, Ann Arbor, Michigan, US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1559-8247","authenticated-orcid":false,"given":"Amit","family":"Awekar","sequence":"additional","affiliation":[{"name":"IIT Guwahati, Guwahati, Assam, IN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,25]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.334"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.144"},{"key":"e_1_3_3_2_5_2","first-page":"3690","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Goyal Saurabh","year":"2020","unstructured":"Saurabh Goyal, Anamitra\u00a0Roy Choudhury, Saurabh Raje, Venkatesan Chakaravarthy, Yogish Sabharwal, and Ashish Verma. 2020. PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination. In Proceedings of the 37th International Conference on Machine Learning. 3690\u20133699. https:\/\/proceedings.mlr.press\/v119\/goyal20a.html"},{"key":"e_1_3_3_2_6_2","unstructured":"Andrey Gromov Kushal Tirumala Hassan Shapourian Paolo Glorioso and Daniel\u00a0A Roberts. 2024. The unreasonable ineffectiveness of the deeper layers. arXiv preprint arXiv:2403.17887 (2024)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Manish Gupta and Puneet Agrawal. 2022. Compression of Deep Learning Models for Text: A Survey. ACM Trans. Knowl. Discov. Data 16 4 Article 61 (jan 2022) 55\u00a0pages. 10.1145\/3487045","DOI":"10.1145\/3487045"},{"key":"e_1_3_3_2_8_2","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_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Xiaoqi Jiao Yichun Yin Lifeng Shang Xin Jiang Xiao Chen Linlin Li Fang Wang and Qun Liu. 2020. TinyBERT: Distilling BERT for Natural Language Understanding. 4163\u20134174. 10.18653\/v1\/2020.findings-emnlp.372","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_3_2_10_2","first-page":"5506","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Kim Sehoon","year":"2021","unstructured":"Sehoon Kim, Amir Gholami, Zhewei Yao, Michael\u00a0W. Mahoney, and Kurt Keutzer. 2021. I-BERT: Integer-only BERT Quantization. In Proceedings of the 38th International Conference on Machine Learning. 5506\u20135518. https:\/\/proceedings.mlr.press\/v139\/kim21d.html"},{"key":"e_1_3_3_2_11_2","volume-title":"8th International Conference on Learning Representations","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In 8th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=H1eA7AEtvS"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1176"},{"key":"e_1_3_3_2_13_2","unstructured":"Xin Men Mingyu Xu Qingyu Zhang Bingning Wang Hongyu Lin Yaojie Lu Xianpei Han and Weipeng Chen. 2024. Shortgpt: Layers in large language models are more redundant than you expect. arXiv preprint arXiv:2403.03853 (2024)."},{"key":"e_1_3_3_2_14_2","volume-title":"International Conference on Learning Representations","author":"Narang Sharan","year":"2017","unstructured":"Sharan Narang, Greg Diamos, Shubho Sengupta, and Erich Elsen. 2017. Exploring Sparsity in Recurrent Neural Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BylSPv9gx"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"David Peer Sebastian Stabinger Stefan Engl and Antonio Rodr\u00edguez-S\u00e1nchez. 2022. Greedy-layer pruning: Speeding up transformer models for natural language processing. Pattern Recognition Letters 157 (2022) 76\u201382. 10.1016\/j.patrec.2022.03.023","DOI":"10.1016\/j.patrec.2022.03.023"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_3_2_17_2","unstructured":"Victor Sanh Lysandre Debut Julien Chaumond and Thomas Wolf. 2019. DistilBERT a distilled version of BERT: smaller faster cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Suraj Srinivas and R\u00a0Venkatesh Babu. 2015. Data-free parameter pruning for deep neural networks. arXiv preprint arXiv:1507.06149 (2015).","DOI":"10.5244\/C.29.31"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"e_1_3_3_2_21_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu Peng","year":"2024","unstructured":"Peng Xu, Wenqi Shao, Mengzhao Chen, Shitao Tang, Kaipeng Zhang, Peng Gao, Fengwei An, Yu Qiao, and Ping Luo. 2024. BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gC6JTEU3jl"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.372"},{"key":"e_1_3_3_2_23_2","unstructured":"Ofir Zafrir Ariel Larey Guy Boudoukh Haihao Shen and Moshe Wasserblat. 2021. Prune once for all: Sparse pre-trained language models. arXiv preprint arXiv:2111.05754 (2021)."}],"event":{"name":"CODS-COMAD 2024: 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)","location":"Jodhpur India","acronym":"CODS-COMAD Dec '24"},"container-title":["Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703323.3703339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T13:04:47Z","timestamp":1750856687000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703323.3703339"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,18]]},"references-count":22,"alternative-id":["10.1145\/3703323.3703339","10.1145\/3703323"],"URL":"https:\/\/doi.org\/10.1145\/3703323.3703339","relation":{},"subject":[],"published":{"date-parts":[[2024,12,18]]},"assertion":[{"value":"2025-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}