{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T02:46:29Z","timestamp":1777430789431,"version":"3.51.4"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2051"],"award-info":[{"award-number":["U23B2051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306084"],"award-info":[{"award-number":["62306084"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen College Stability Support Plan","award":["GXWD20231128102243003"],"award-info":[{"award-number":["GXWD20231128102243003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3416316","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T17:43:21Z","timestamp":1718732601000},"page":"9023-9037","source":"Crossref","is-referenced-by-count":10,"title":["Influence Function Based Second-Order Channel Pruning: Evaluating True Loss Changes for Pruning is Possible Without Retraining"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4766-8935","authenticated-orcid":false,"given":"Hongrong","family":"Cheng","sequence":"first","affiliation":[{"name":"University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1262-4174","authenticated-orcid":false,"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9126-2107","authenticated-orcid":false,"given":"Javen Qinfeng","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00747"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00867"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref5","article-title":"Natural language descriptions of deep visual features","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hernandez"},{"key":"ref6","article-title":"Towards efficient end-to-end speech recognition with biologically-inspired neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bohnstingl"},{"key":"ref7","article-title":"Audio lottery: Speech recognition made ultra-lightweight, transferable, and noise-robust","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ding"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"ref9","first-page":"2130","article-title":"Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"You"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref11","first-page":"7021","article-title":"Group fisher pruning for practical network compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref12","first-page":"25668","article-title":"The combinatorial brain surgeon: Pruning weights that cancel one another in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref13","article-title":"SOSP: Efficiently capturing global correlations by second-order structured pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nonnenmacher"},{"key":"ref14","first-page":"3760","article-title":"Linearity grafting: Relaxed neuron pruning helps certifiable robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01211"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00923"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01064"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00368"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01159"},{"key":"ref24","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref25","first-page":"12557","article-title":"iDARTS: Differentiable architecture search with stochastic implicit gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref26","first-page":"8635","article-title":"Sparse double descent: Where network pruning aggravates overfitting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He"},{"key":"ref27","article-title":"Long live the lottery: The existence of winning tickets in lifelong learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref28","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref29","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","author":"Wen"},{"key":"ref30","article-title":"Pruning filters for efficient ConvNets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref31","article-title":"Advancing model pruning via bi-level optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref32","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Molchanov"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17046"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref36","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref37","article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"ref39","article-title":"Drawing early-bird tickets: Towards more efficient training of deep networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"You"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref43","article-title":"Rethinking the smaller-norm-less-informative assumption in channel pruning of convolution layers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ye"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref45","first-page":"4857","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00153"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1980.10486199"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1974.10482962"},{"key":"ref50","first-page":"715","article-title":"On second-order group influence functions for black-box predictions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Basu"},{"key":"ref51","article-title":"Resolving training biases via influence-based data relabeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong"},{"key":"ref52","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lorraine"},{"key":"ref53","article-title":"On the convergence of stochastic bi-level gradient methods","author":"Couellan","year":"2016","journal-title":"Optimization"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01206"},{"key":"ref55","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref56","first-page":"9833","article-title":"Training your sparse neural network better with any mask","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaiswal"},{"key":"ref57","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.58"},{"key":"ref59","article-title":"WoodFisher: Efficient second-order approximation for neural network compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Singh"},{"key":"ref60","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref61","first-page":"26693","article-title":"Revisiting and advancing fast adversarial training through the lens of bi-level optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref66","first-page":"1130","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref67","article-title":"OpenMMLab\u2019s image classification toolbox and benchmark","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/309"},{"key":"ref70","first-page":"5122","article-title":"Operation-aware soft channel pruning using differentiable masks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3088323"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00637"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6910"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00290"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref77","first-page":"883","article-title":"Discrimination-aware channel pruning for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhuang"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/336"},{"key":"ref79","article-title":"MMDetection","author":"Chen","year":"2018"},{"key":"ref80","article-title":"Sanity-checking pruning methods: Random tickets can win the jackpot","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Su"},{"key":"ref81","article-title":"Picking winning tickets before training by preserving gradient flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10561558.pdf?arnumber=10561558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:27:45Z","timestamp":1732667265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10561558\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":81,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3416316","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":[[2024,12]]}}}