{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:38:27Z","timestamp":1776883107589,"version":"3.51.2"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MTC Programmatic Funds","award":["M23L7b0021"],"award-info":[{"award-number":["M23L7b0021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tpami.2025.3586418","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T13:49:45Z","timestamp":1751896185000},"page":"9298-9315","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Distortion-Minimized Layerwise Pruning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7222-2628","authenticated-orcid":false,"given":"Kaixin","family":"Xu","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2830-030X","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runtao","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2594-9648","authenticated-orcid":false,"given":"Xue","family":"Geng","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8971-0660","authenticated-orcid":false,"given":"Jie","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7002-4564","authenticated-orcid":false,"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0977-3600","authenticated-orcid":false,"given":"Min","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-6562","authenticated-orcid":false,"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency of Science, Technology and Research, A*STAR, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-1947","authenticated-orcid":false,"given":"Weisi","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science (CCDS), Nanyang Technological University (NTU), Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015"},{"key":"ref3","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref4","first-page":"4932","article-title":"One ticket to win them all: Generalizing lottery ticket initializations across datasets and optimizers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Morcos"},{"key":"ref5","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref6","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2018"},{"key":"ref7","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019"},{"key":"ref8","first-page":"3821","article-title":"An information-theoretic justification for model pruning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Isik"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref10","article-title":"Learning to prune deep neural networks via reinforcement learning","author":"Gupta","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803498"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DCC50243.2021.00033"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01600"},{"key":"ref15","first-page":"30","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Molchanov"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00144"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref21","article-title":"Scientific control for reliable neural network pruning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref23","first-page":"12 894","article-title":"Structural pruning via latency-saliency knapsack","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref24","first-page":"2031","article-title":"Fast as chita: Neural network pruning with combinatorial optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Benbaki"},{"key":"ref25","first-page":"19 637","article-title":"Only train once: A one-shot neural network training and pruning framework","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01530"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681419"},{"key":"ref28","article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00540"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29108"},{"key":"ref31","first-page":"19 974","article-title":"Chasing sparsity in vision transformers: An end-to-end exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref32","article-title":"Unified visual transformer compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01779"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29296"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13350"},{"key":"ref38","article-title":"Lite transformer with long-short range attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref40","first-page":"17 283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref41","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref42","first-page":"24 898","article-title":"IA-RED$^{2}$2: Interpretability-aware redundancy reduction for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref43","article-title":"CP-ViT: Cascade vision transformer pruning via progressive sparsity prediction","author":"Song","year":"2022"},{"key":"ref44","article-title":"Data-independent module-aware pruning for hierarchical vision transformers","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"He"},{"key":"ref45","article-title":"Preserving deep representations in one-shot pruning: A hessian-free second-order optimization framework","author":"Lucas","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11623"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"ref49","article-title":"SNIP: Single-shot network pruning based on connection sensitivity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref50","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref55","first-page":"2943","article-title":"Rigging the lottery: Making all tickets winners","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evci"},{"key":"ref56","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref58","article-title":"Vision transformer pruning","author":"Zhu","year":"2021"},{"key":"ref59","article-title":"Dynamic model pruning with feedback","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19888"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222632"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01625"},{"key":"ref66","first-page":"6735","article-title":"Spatial pruned sparse convolution for efficient 3D object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16207"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11072282.pdf?arnumber=11072282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:21Z","timestamp":1758028281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11072282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3586418","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}