{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:28:01Z","timestamp":1777994881681,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100011066","name":"Hong Kong Research Grants Council","doi-asserted-by":"publisher","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}],"id":[{"id":"10.13039\/501100011066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC\/RGC","doi-asserted-by":"publisher","award":["CRS_HKUST603\/22"],"award-info":[{"award-number":["CRS_HKUST603\/22"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010256","name":"Guangzhou Municipal Science and Technology Project","doi-asserted-by":"publisher","award":["2023A03J001l"],"award-info":[{"award-number":["2023A03J001l"]}],"id":[{"id":"10.13039\/501100010256","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,29]]},"DOI":"10.1109\/ieeeconf59524.2023.10476886","type":"proceedings-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T19:28:52Z","timestamp":1711999732000},"page":"1600-1604","source":"Crossref","is-referenced-by-count":1,"title":["Mode Connectivity in Federated Learning with Data Heterogeneity"],"prefix":"10.1109","author":[{"given":"Tailin","family":"Zhou","sequence":"first","affiliation":[{"name":"Academy of Interdisciplinary Studies, The Hong Kong University of Science and Technology,IPO,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danny H.K.","family":"Tsang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou),Internet of Things Thrust,Guangzhou,Guangdong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref3","doi-asserted-by":"crossref","volume-title":"Federated learning with non-iid data","author":"Zhao","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"ref4","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS), Virtual Event","author":"Wang","year":"2020"},{"key":"ref5","volume-title":"A survey of what to share in federated learning: Perspectives on model utility, privacy leakage, and communication efficiency","author":"Shao"},{"key":"ref6","first-page":"8803","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Garipov"},{"issue":"10\u201315","key":"ref7","first-page":"1309","article-title":"Essentially no barriers in neural network energy landscape","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Draxler","year":"2018"},{"key":"ref8","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Li"},{"key":"ref9","volume-title":"Mimic: Combating client dropouts in federated learning by mimicking central updates","author":"Sun"},{"key":"ref10","first-page":"5972","article-title":"No fear of heterogeneity: Classifier calibration for federated learning with non-iid data","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Luo","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3325366"},{"key":"ref12","volume-title":"Fedcir: Client-invariant representation learning for federated non-iid features","author":"Li"},{"key":"ref13","article-title":"Topology and geometry of half-rectified network optimization","volume-title":"Proc. Int. Conf. Learn. Repr. (ICLR)","author":"Freeman"},{"key":"ref14","article-title":"Understanding federated learning through loss landscape visualizations: A pilot study","volume-title":"Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022)","author":"Li","year":"2022"},{"key":"ref15","doi-asserted-by":"crossref","volume-title":"Understanding and improving model averaging in federated learning on heterogeneous data","author":"Zhou","DOI":"10.1109\/TMC.2024.3406554"},{"key":"ref16","first-page":"14574","article-title":"Explaining landscape connectivity of low-cost solutions for multilayer nets","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Kuditipudi"},{"key":"ref17","first-page":"8773","article-title":"Landscape connectivity and dropout stability of SGD solutions for over-parameterized neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Shevchenko","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref21","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Repr. (ICLR)","author":"Simonyan"},{"key":"ref22","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Yurochkin"},{"issue":"11","key":"ref23","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","article-title":"The role of permutation invariance in linear mode connectivity of neural networks","volume-title":"Proc. Int. Conf. Learn. Repr. (ICLR)","author":"Entezari","year":"2022"}],"event":{"name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2023,10,29]]},"end":{"date-parts":[[2023,11,1]]}},"container-title":["2023 57th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10476702\/10476779\/10476886.pdf?arnumber=10476886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T12:31:55Z","timestamp":1731673915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf59524.2023.10476886","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]}}}