{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:55:27Z","timestamp":1761396927439,"version":"3.37.3"},"reference-count":44,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62301487"],"award-info":[{"award-number":["62301487"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ23F010021"],"award-info":[{"award-number":["LQ23F010021"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2203214"],"award-info":[{"award-number":["ECCS-2203214"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Infocomm Media Development Authority under its Future Communications Research & Development Programme"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tsp.2024.3454986","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T17:27:26Z","timestamp":1726853246000},"page":"5140-5155","source":"Crossref","is-referenced-by-count":2,"title":["Magnitude Matters: Fixing signSGD Through Magnitude-Aware Sparsification and Error Feedback in the Presence of Data Heterogeneity"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1480-585X","authenticated-orcid":false,"given":"Richeng","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9254-9062","authenticated-orcid":false,"given":"Xiaofan","family":"He","sequence":"additional","affiliation":[{"name":"Electronic Information School, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9960-7800","authenticated-orcid":false,"given":"Caijun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2346-6228","authenticated-orcid":false,"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4037-3149","authenticated-orcid":false,"given":"Tony Q. S.","family":"Quek","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0078-4891","authenticated-orcid":false,"given":"Huaiyu","family":"Dai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900491"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016905"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3125601"},{"key":"ref4","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dean","year":"2012"},{"key":"ref5","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref6","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Stich","year":"2019"},{"key":"ref7","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh","year":"2017"},{"key":"ref8","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Reisizadeh","year":"2020"},{"key":"ref9","first-page":"2350","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Haddadpour","year":"2021"},{"key":"ref10","first-page":"1509","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2983166"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3244092"},{"key":"ref14","first-page":"4447","article-title":"Sparsified SGD with memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stich","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2981904"},{"key":"ref16","first-page":"5973","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh","year":"2018"},{"key":"ref17","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2020.2985917"},{"key":"ref19","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Bernstein","year":"2018"},{"key":"ref20","first-page":"21616","article-title":"Distributed training with heterogeneous data: Bridging median- and mean-based algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref22","first-page":"3252","article-title":"Error feedback fixes signSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Karimireddy","year":"2019"},{"key":"ref23","first-page":"11450","article-title":"Communication-efficient distributed blockwise momentum SGD with error-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zheng","year":"2019"},{"key":"ref24","first-page":"9224","article-title":"Stochastic sign descent methods: New algorithms and better theory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Safaryan","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2015.2505684"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3039309"},{"article-title":"Stochastic-sign SGD for federated learning with theoretical guarantees","year":"2020","author":"Jin","key":"ref28"},{"key":"ref29","first-page":"8253","article-title":"FetchSGD: Communication-efficient federated learning with sketching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rothchild","year":"2020"},{"key":"ref30","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Wangni","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852172"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3106104"},{"key":"ref34","first-page":"26 048","article-title":"Understanding clipping for federated learning: Convergence and client-level differential privacy","volume-title":"Proc. Int. Conf. Mach. Learn., PMLR","author":"Zhang","year":"2022"},{"key":"ref35","first-page":"13773","article-title":"Understanding gradient clipping in private SGD: A geometric perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref36","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2021"},{"key":"ref37","article-title":"On the convergence of FedAvg on non-i.i.d data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref38","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2020"},{"key":"ref39","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00119"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Measuring the effects of non-identical data distribution for federated visual classification","year":"2019","author":"Hsu","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1966.1053907"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10347386\/10685055.pdf?arnumber=10685055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:58:26Z","timestamp":1732665506000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10685055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tsp.2024.3454986","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2024]]}}}