{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:47Z","timestamp":1740169367632,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Chung-Ang University Graduate Research Scholarship in 2022"},{"name":"Institute for Information and Communication Technology Planning and Evaluation"},{"name":"Korean Government [Ministry of Science and Information and Communication Technology (MSIT)] through the Chung-Ang University Artificial Intelligence Graduate School Program","award":["2021-0-01341"],"award-info":[{"award-number":["2021-0-01341"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-RS-2023-00251366"],"award-info":[{"award-number":["NRF-RS-2023-00251366"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2023.3346697","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:13:53Z","timestamp":1703535233000},"page":"157-167","source":"Crossref","is-referenced-by-count":0,"title":["Splitting of Composite Neural Networks via Proximal Operator With Information Bottleneck"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9983-3316","authenticated-orcid":false,"given":"Sang-Il","family":"Han","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6858-3551","authenticated-orcid":false,"given":"Kensuke","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3939","authenticated-orcid":false,"given":"Byung-Woo","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100134"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13428-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"issue":"7","key":"ref6","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref8","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2400000003"},{"key":"ref10","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref11","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013","journal-title":"arXiv:1312.6114"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref13","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"issue":"3","key":"ref16","first-page":"543","article-title":"A method of solving a convex programming problem with convergence rate O(1\/k\u00b2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Doklady Akademii Nauk"},{"key":"ref17","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref18","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref19","article-title":"AdamP: Slowing down the slowdown for momentum optimizers on scale-invariant weights","author":"Heo","year":"2020","journal-title":"arXiv:2006.08217"},{"key":"ref20","first-page":"1","article-title":"Incorporating Nesterov momentum into Adam","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Dozat"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.03265"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3208223"},{"key":"ref23","first-page":"11448","article-title":"Positive-negative momentum: Manipulating stochastic gradient noise to improve generalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref24","article-title":"Adan: Adaptive Nesterov momentum algorithm for faster optimizing deep models","author":"Xie","year":"2022","journal-title":"arXiv:2208.06677"},{"key":"ref25","article-title":"MINE: Mutual information neural estimation","author":"Belghazi","year":"2018","journal-title":"arXiv:1801.04062"},{"key":"ref26","article-title":"Estimating information flow in deep neural networks","author":"Goldfeld","year":"2018","journal-title":"arXiv:1810.05728"},{"key":"ref27","article-title":"Information bottleneck: Exact analysis of (quantized) neural networks","author":"Lorenzen","year":"2021","journal-title":"arXiv:2106.12912"},{"key":"ref28","article-title":"Deep variational information bottleneck","author":"Alemi","year":"2016","journal-title":"arXiv:1612.00410"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2784440"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref36","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref37","first-page":"1437","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Falkner"},{"key":"ref38","article-title":"Model-based asynchronous hyperparameter and neural architecture search","author":"Klein","year":"2020","journal-title":"arXiv:2003.10865"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2015.2439281"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.182"},{"key":"ref45","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00453"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00328"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038535"},{"key":"ref49","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref50","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3196503"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119645"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10373031.pdf?arnumber=10373031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T05:19:51Z","timestamp":1706073591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10373031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3346697","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}