{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T03:39:35Z","timestamp":1773113975053,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T00:00:00Z","timestamp":1710460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Federal Ministry for Digital and Transport (BMVI) in the Projects \u201cKIVI\u2014KI im Verkehr Ingolstadt\u201d and \u201c5GoIng\u20145G Innovation Concept Ingolstadt.\u201d"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,3,15]]},"DOI":"10.1109\/jiot.2023.3324079","type":"journal-article","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T17:48:29Z","timestamp":1697132909000},"page":"9458-9472","source":"Crossref","is-referenced-by-count":14,"title":["ResFed: Communication-Efficient Federated Learning With Deep Compressed Residuals"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7359-1081","authenticated-orcid":false,"given":"Rui","family":"Song","sequence":"first","affiliation":[{"name":"Connected Mobility and Infrastructure, Fraunhofer Institute for Transportation and Infrastructure Systems IVI, Ingolstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2767-2598","authenticated-orcid":false,"given":"Liguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Garching, Germany"}]},{"given":"Lingjuan","family":"Lyu","sequence":"additional","affiliation":[{"name":"PPML Team, Sony AI, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5254-6425","authenticated-orcid":false,"given":"Andreas","family":"Festag","sequence":"additional","affiliation":[{"name":"Connected Mobility and Infrastructure, Fraunhofer Institute for Transportation and Infrastructure Systems IVI, Ingolstadt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-Time Systems, Technical University of Munich, Garching, Germany"}]}],"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. Stat. (AISTATS 2017)","volume":"54","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3216981"},{"key":"ref3","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"Keskar","year":"2019","journal-title":"arXiv:1909.05858"},{"issue":"140","key":"ref4","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922064"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3041185"},{"key":"ref7","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","volume-title":"Proc. Int. Conf. Artif. Intell. Stat. (AISTATS 2020)","author":"Reisizadeh"},{"key":"ref8","first-page":"8852","article-title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML 2022)","author":"H\u00f6nig"},{"key":"ref9","first-page":"1","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29763-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191879"},{"key":"ref12","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS 2021)","author":"Li"},{"key":"ref13","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR 2016)","author":"Han"},{"key":"ref14","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst. (MLSys 2020)","volume":"2","author":"Li"},{"key":"ref15","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS 2020)"},{"key":"ref16","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML 2020)","volume":"119","author":"Karimireddy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2019.8852172"},{"key":"ref18","first-page":"5332","article-title":"Federated accelerated stochastic gradient descent","volume-title":"Proc. 34th Neural Inf. Process. Syst. (NeurIPS 2020)","volume":"33","author":"Yuan"},{"key":"ref19","first-page":"3973","article-title":"FedBoost: A communicationefficient algorithm for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML 2020)","author":"Hamer"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611781"},{"issue":"8","key":"ref21","first-page":"8432","article-title":"Fedproto: Federated prototype learning across heterogeneous clients","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"36","author":"Tan"},{"key":"ref22","first-page":"25501","article-title":"QSFL: A two-level uplink communication optimization framework for federated learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML 2022)","volume":"162","author":"Yi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3142678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/12.227952"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/jsait.2020.3042094"},{"key":"ref26","article-title":"Optimizing the communication-accuracy trade-off in federated learning with rate-distortion theory","author":"Mitchell","year":"2022","journal-title":"arXiv:2201.02664"},{"key":"ref27","first-page":"3821","article-title":"An information-theoretic justification for model pruning","volume-title":"Proc. Int. Conf. Artif. Intell. Stat. (AISTATS 2022)","author":"Isik"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ieeeconf44664.2019.9049052"},{"key":"ref29","article-title":"Understanding top-k sparsification in distributed deep learning","author":"Shi","year":"2019","journal-title":"arXiv:1911.08772"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/infocom41043.2020.9155269"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1045"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/473"},{"key":"ref33","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS 2017)","volume":"30","author":"Lian"},{"key":"ref34","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML 2018)","volume":"80","author":"Bernstein"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2021.3073112"},{"key":"ref36","article-title":"LEAF: A benchmark for federated settings","author":"Caldas","year":"2018","journal-title":"arXiv:1812.01097"},{"key":"ref37","article-title":"Fair resource allocation in federated learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref38","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010","journal-title":"arXiv:1812.01097"},{"key":"ref39","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:cs.LG\/1708.07747"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2017.7966217"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00985"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102993"},{"key":"ref45","first-page":"1","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. 32nd Neural Inf. Process. Syst. (NeurIPS 2018)","volume":"31","author":"Alistarh"},{"key":"ref46","first-page":"382","article-title":"On the construction of Huffman trees","volume-title":"Proc. 3rd Int. Colloq. Automatacia Lang. Program. (ICALP 1976)","author":"Van Leeuwen"},{"key":"ref47","first-page":"11761","article-title":"EF21-P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Gruntkowska"},{"key":"ref48","article-title":"EF21: A new, simpler, theoretically better, and practically faster error feedback","volume-title":"Advances in Neural Information Processing Systems","author":"Richt\u00e1rik","year":"2021"},{"key":"ref49","first-page":"1","article-title":"Momentum provably improves error feedback!","volume-title":"Proc. ICML","author":"Fatkhullin"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10463544\/10283999.pdf?arnumber=10283999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T21:17:56Z","timestamp":1711487876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10283999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,15]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3324079","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,15]]}}}