{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:44:41Z","timestamp":1781779481775,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["RS-2024-00409492"],"award-info":[{"award-number":["RS-2024-00409492"]}]},{"name":"Korean Government","award":["RS-2024-00334904"],"award-info":[{"award-number":["RS-2024-00334904"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tnnls.2025.3590015","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:45:16Z","timestamp":1755546316000},"page":"19805-19819","source":"Crossref","is-referenced-by-count":2,"title":["FedLSC: Improving Communication Efficiency and Robustness in Federated Learning With Stragglers and Adversaries"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1828-6441","authenticated-orcid":false,"given":"Hyeong-Gun","family":"Joo","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9535-2521","authenticated-orcid":false,"given":"Songnam","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5017-5314","authenticated-orcid":false,"given":"Dong-Joon","family":"Shin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105810"},{"key":"ref3","first-page":"13480","article-title":"A unified solution for privacy and communication efficiency in vertical federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3294295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152581"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3271859"},{"key":"ref8","first-page":"4566","article-title":"Guardhfl: Privacy guardian for heterogeneous federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3370297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264740"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129809"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3316672"},{"key":"ref13","first-page":"61213","article-title":"A3fl: Adversarially adaptive backdoor attacks to federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3167482"},{"key":"ref15","first-page":"73258","article-title":"Fluid: Mitigating stragglers in federated learning using invariant dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref16","first-page":"840","article-title":"Sageflow: Robust federated learning against both stragglers and adversaries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Park"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3131614"},{"key":"ref18","first-page":"8356","article-title":"DoCoFL: Downlink compression for cross-device federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dorfman"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041185"},{"key":"ref21","first-page":"9955","article-title":"Robustness to unbounded smoothness of generalized SignSGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Crawshaw"},{"key":"ref22","first-page":"62428","article-title":"EvoFed: Leveraging evolutionary strategies for communication-efficient federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rahimi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3333804"},{"key":"ref24","first-page":"3757","article-title":"LESS-VFL: Communication-efficient feature selection for vertical federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Castiglia"},{"key":"ref25","first-page":"33027","article-title":"SimFBO: Towards simple, flexible and communication-efficient federated bilevel learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3345367"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250658"},{"key":"ref28","first-page":"12876","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Horv\u00e1th"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278563"},{"key":"ref30","first-page":"141292","article-title":"Discovering sparsity allocation for layer-wise pruning of large language models","volume-title":"Proc. The 38th Annu. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Li"},{"key":"ref31","article-title":"AlphaPruning: Using heavy-tailed self regularization theory for improved layer-wise pruning of large language models","author":"Lu","year":"2024","journal-title":"arXiv:2410.10912"},{"key":"ref32","article-title":"FreezeOut: Accelerate training by progressively freezing layers","author":"Brock","year":"2017","journal-title":"arXiv:1706.04983"},{"key":"ref33","article-title":"Accelerating deep learning inference via freezing","volume-title":"Proc. 11th USENIX Workshop Hot Topics Cloud Comput.","author":"Kumar"},{"key":"ref34","first-page":"14011","article-title":"Accelerating training of transformer-based language models with progressive layer dropping","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00312-x"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3350241"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26023"},{"key":"ref38","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Zinkevich"},{"key":"ref39","first-page":"1508","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Wen"},{"key":"ref40","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Alistarh"},{"key":"ref41","first-page":"560","article-title":"Signsgd: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Bernstein"},{"key":"ref42","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref43","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\\\u2019{y}","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref44","article-title":"The convergence of sparsified gradient methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Alistarh"},{"key":"ref45","article-title":"The geometry of sign gradient descent","author":"Balles","year":"2020","journal-title":"arXiv:2002.08056"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3280938"},{"key":"ref47","article-title":"Poisoning attacks against support vector machines","author":"Biggio","year":"2012","journal-title":"arXiv:1206.6389"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386863"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38794-x"},{"key":"ref50","first-page":"10495","article-title":"Zeno++: Robust fully asynchronous SGD","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref51","article-title":"Practical one-shot federated learning for cross-silo setting","author":"Li","year":"2020","journal-title":"arXiv:2010.01017"},{"key":"ref52","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref53","volume-title":"Pearson Correlation Coefficient\u2014Wikipedia, the Free Encyclopedia","year":"2024"},{"key":"ref54","article-title":"Natasha 2: Faster non-convex optimization than SGD","author":"Allen-Zhu","year":"2017","journal-title":"arXiv:1708.08694"},{"key":"ref55","article-title":"SignSGD with majority vote is communication efficient and fault tolerant","author":"Bernstein","year":"2018","journal-title":"arXiv:1810.05291"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref57","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11220834\/11127200.pdf?arnumber=11127200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:03:24Z","timestamp":1761847404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":57,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3590015","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}