{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:37Z","timestamp":1787017417756,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"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":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671780","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T00:55:12Z","timestamp":1724547312000},"page":"2775-2783","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Dual-Assessment Driven Pruning: Iterative Optimizing Layer-wise Sparsity for Large Language Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8403-0463","authenticated-orcid":false,"given":"Qinghui","family":"Sun","sequence":"first","affiliation":[{"name":"Alibaba Group, HangZhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8864-4374","authenticated-orcid":false,"given":"Weilun","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, HangZhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0000-6740","authenticated-orcid":false,"given":"Yanni","family":"Zhu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9348-0029","authenticated-orcid":false,"given":"Shenghuan","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8167-2113","authenticated-orcid":false,"given":"Hao","family":"Yi","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4980-6408","authenticated-orcid":false,"given":"Zehua","family":"Cai","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8790-7478","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"June","year":"2018","unstructured":"Radford, Alec, and et al. Improving language understanding by generative pretraining. OpenAI blog, June 2018."},{"key":"e_1_3_2_2_2_1","volume-title":"Feb","year":"2019","unstructured":"Radford, Alec, and et al. Improving language understanding by generative pretraining. OpenAI blog, 1(8), Feb 2019."},{"key":"e_1_3_2_2_3_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems","year":"2020","unstructured":"Brown, Tom, and et al. Language models are few-shot learners. Advances in neural information processing systems, 33, July 2020."},{"key":"e_1_3_2_2_4_1","volume-title":"March","author":"AI.","year":"2022","unstructured":"OpenAI. Training language models to follow instructions with human feedback. arXiv preprint, March 2022."},{"key":"e_1_3_2_2_5_1","first-page":"35","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","author":"Elias Frantar","year":"2022","unstructured":"Frantar Elias and Dan Alistarh. Optimal brain compression: A framework for accurate post-training quantization and pruning. Advances in Neural Information Processing Systems, 35, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_6_1","volume-title":"int8 (): 8-bit matrix multiplication for transformers at scale. arXiv preprint","year":"2022","unstructured":"Dettmers, Tim, and et al. Llm. int8 (): 8-bit matrix multiplication for transformers at scale. arXiv preprint, 2022."},{"key":"e_1_3_2_2_7_1","volume-title":"International Conference on Machine Learning","year":"2023","unstructured":"Xiao, Guangxuan, and et al. Smoothquant: Accurate and efficient post-training quantization for large language models. International Conference on Machine Learning, 2023."},{"key":"e_1_3_2_2_8_1","volume-title":"March","year":"2023","unstructured":"Frantar, Elias, and et al. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint, March 2023."},{"key":"e_1_3_2_2_9_1","volume-title":"Spqr: A sparse-quantized representation for nearlossless llm weight compression. arXiv preprint","year":"2023","unstructured":"Dettmers, Tim, and et al. Spqr: A sparse-quantized representation for nearlossless llm weight compression. arXiv preprint, 2023."},{"key":"e_1_3_2_2_10_1","volume-title":"March","year":"2024","unstructured":"Chee, Jerry, and et al. Quip: 2-bit quantization of large language models with guarantees. arXiv preprint, March 2024."},{"key":"e_1_3_2_2_11_1","volume-title":"Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4)","year":"1989","unstructured":"LeCun, Yann, and et al. Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4), 1989."},{"key":"e_1_3_2_2_12_1","volume-title":"Optimal brain damage. Advances in neural information processing systems, 2","year":"1989","unstructured":"LeCun, Yann, and et al. Optimal brain damage. Advances in neural information processing systems, 2, 1989."},{"key":"e_1_3_2_2_13_1","volume-title":"IEEE international conference on neural networks","year":"1993","unstructured":"Hassibi, Stork, and et al. Optimal brain surgeon and general network pruning. IEEE international conference on neural networks, 1993."},{"key":"e_1_3_2_2_14_1","volume-title":"Learning both weights and connections for efficient neural network. Advances in neural information processing systems, 28","year":"2015","unstructured":"Han, Song, and et al. Learning both weights and connections for efficient neural network. Advances in neural information processing systems, 28, 2015."},{"key":"e_1_3_2_2_15_1","volume-title":"International Conference on Machine Learning","author":"Elias Frantar","year":"2023","unstructured":"Frantar Elias and Dan Alistarh. Sparsegpt: Massive language models can be accurately pruned in one-shot. International Conference on Machine Learning, 2023."},{"key":"e_1_3_2_2_16_1","volume-title":"A simple and effective pruning approach for large language models. arXiv preprint","year":"2023","unstructured":"Sun, Mingjie, and et al. A simple and effective pruning approach for large language models. arXiv preprint, 2023."},{"key":"e_1_3_2_2_17_1","volume-title":"Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity. arXiv preprint","author":"Yin Lu","year":"2023","unstructured":"Lu Yin, You Wu, and et al. Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity. arXiv preprint, 2023."},{"key":"e_1_3_2_2_18_1","volume-title":"Skeletonization: A technique for trimming the fat from a network via relevance assessment. Advances in neural information processing systems, 1","author":"Mozer Michael C","year":"1988","unstructured":"Michael C Mozer and Paul Smolensky. Skeletonization: A technique for trimming the fat from a network via relevance assessment. Advances in neural information processing systems, 1, 1988."},{"key":"e_1_3_2_2_19_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. Learning both weights and connections for efficient neural network. Advances in neural information processing systems, 28, 2015."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04316-3"},{"key":"e_1_3_2_2_21_1","volume-title":"Learning intrinsic sparse structures within long short-term memory. arXiv preprint arXiv:1709.05027","author":"Wen Wei","year":"2017","unstructured":"Wei Wen, Yuxiong He, Samyam Rajbhandari, Minjia Zhang, Wenhan Wang, Fang Liu, Bin Hu, Yiran Chen, and Hai Li. Learning intrinsic sparse structures within long short-term memory. arXiv preprint arXiv:1709.05027, 2017."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"e_1_3_2_2_23_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Ma Xinyin","year":"2023","unstructured":"Xinyin Ma, Gongfan Fang, and et al. Llm-pruner: On the structural pruning of large language models. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_3_2_2_24_1","volume-title":"Loraprune: Pruning meets low-rank parameter-efficient fine-tuning. arXiv preprint","author":"Zhang Mingyang","year":"2023","unstructured":"Mingyang Zhang, Hao Chen, and et al. Loraprune: Pruning meets low-rank parameter-efficient fine-tuning. arXiv preprint, 2023."},{"key":"e_1_3_2_2_25_1","volume-title":"Lorashear: Efficient large language model structured pruning and knowledge recovery. arXiv preprint","author":"Chen Tianyi","year":"2023","unstructured":"Tianyi Chen, Tianyu Ding, and et al. Lorashear: Efficient large language model structured pruning and knowledge recovery. arXiv preprint, 2023."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5570-z"},{"key":"e_1_3_2_2_27_1","series-title":"Proceedings of Machine Learning Research","first-page":"2943","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Evci Utku","year":"2020","unstructured":"Utku Evci, Trevor Gale, and et al. Rigging the lottery: Making all tickets winners. In Hal Daum\u00e9 III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 2943--2952. PMLR, 13-18 Jul 2020."},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Learning Representations","author":"Liu Shiwei","year":"2022","unstructured":"Shiwei Liu, Tianlong Chen, and et al. The unreasonable effectiveness of random pruning: Return of the most naive baseline for sparse training. In International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Learning Representations","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle, Michael Carbin, and et al. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In International Conference on Learning Representations, 2019."},{"key":"e_1_3_2_2_30_1","volume-title":"International Conference on Learning Representations","author":"Lee Jaeho","year":"2021","unstructured":"Jaeho Lee, Sejun Park, and et al. Layer-adaptive sparsity for the magnitude-based pruning. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_2_31_1","volume-title":"Sparse training via boosting pruning plasticity with neuroregeneration","author":"Liu Shiwei","year":"2022","unstructured":"Shiwei Liu, Tianlong Chen, and et al. Sparse training via boosting pruning plasticity with neuroregeneration, 2022."},{"key":"e_1_3_2_2_32_1","volume-title":"Compressing llms: The truth is rarely pure and never simple","author":"Jaiswal Ajay","year":"2023","unstructured":"Ajay Jaiswal, Zhe Gan, Xianzhi Du, Bowen Zhang, Zhangyang Wang, and Yinfei Yang. Compressing llms: The truth is rarely pure and never simple, 2023."},{"key":"e_1_3_2_2_33_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. Opt: Open pre-trained transformer language models","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. Opt: Open pre-trained transformer language models, 2022."},{"key":"e_1_3_2_2_34_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. Llama 2: Open foundation and fine-tuned chat models 2023."},{"key":"e_1_3_2_2_35_1","volume-title":"Pointer sentinel mixture models","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. Pointer sentinel mixture models, 2016."},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of a Workshop held at Plainsboro","author":"Marcus Mitchell P.","year":"1994","unstructured":"Mitchell P. Marcus, Grace Kim, Mary Ann Marcinkiewicz, Robert MacIntyre, Ann Bies, Mark Ferguson, Karen Katz, and Britta Schasberger. The penn treebank: Annotating predicate argument structure. In Human Language Technology, Proceedings of a Workshop held at Plainsboro, New Jerey, USA, March 8-11, 1994. Morgan Kaufmann, 1994."},{"key":"e_1_3_2_2_37_1","volume-title":"Boolq: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark Christopher","year":"2019","unstructured":"Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. Boolq: Exploring the surprising difficulty of natural yes\/no questions, 2019."},{"key":"e_1_3_2_2_38_1","volume-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. Glue: A multi-task benchmark and analysis platform for natural language understanding, 2019."},{"key":"e_1_3_2_2_39_1","volume-title":"Hellaswag: Can a machine really finish your sentence?","author":"Zellers Rowan","year":"2019","unstructured":"Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. Hellaswag: Can a machine really finish your sentence?, 2019."},{"key":"e_1_3_2_2_40_1","volume-title":"Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale","author":"Sakaguchi Keisuke","year":"2019","unstructured":"Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale, 2019."},{"key":"e_1_3_2_2_41_1","volume-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","author":"Clark Peter","year":"2018","unstructured":"Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. Think you have solved question answering? try arc, the ai2 reasoning challenge, 2018."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"e_1_3_2_2_43_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel Colin","year":"2023","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer, 2023."},{"key":"e_1_3_2_2_44_1","volume-title":"Accelerated sparse neural training: A provable and efficient method to find n:m transposable masks","author":"Hubara Itay","year":"2021","unstructured":"Itay Hubara, Brian Chmiel, Moshe Island, Ron Banner, Seffi Naor, and Daniel Soudry. Accelerated sparse neural training: A provable and efficient method to find n:m transposable masks, 2021."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671780","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671780","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:04:13Z","timestamp":1750277053000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671780"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":44,"alternative-id":["10.1145\/3637528.3671780","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671780","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}