{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:47:41Z","timestamp":1765889261422},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1109\/globecom54140.2023.10437811","type":"proceedings-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T19:45:36Z","timestamp":1708976736000},"page":"5280-5285","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Top- K in SGD for Communication-Efficient Distributed Learning"],"prefix":"10.1109","author":[{"given":"Mengzhe","family":"Ruan","sequence":"first","affiliation":[{"name":"City University of Hong Kong Shenzhen Research Institute,Shenzhen,China"}]},{"given":"Guangfeng","family":"Yan","sequence":"additional","affiliation":[{"name":"City University of Hong Kong Shenzhen Research Institute,Shenzhen,China"}]},{"given":"Yuanzhang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Hawaii Advanced Wireless Technologies Institute, University of Hawaii at Manoa,Honolulu,HI,USA"}]},{"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"City University of Hong Kong Shenzhen Research Institute,Shenzhen,China"}]},{"given":"Weitao","family":"Xu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong Shenzhen Research Institute,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Large scale distributed deep networks","volume-title":"in Proceedings of Conference in Neural Information Processing Systems (NeurIPS)","author":"Dean","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126060"},{"key":"ref3","article-title":"On the Convergence of FedAvg on Non-IID Data","volume-title":"Proceedings of International Conference on Learning Representations (ICLR)","author":"Li","year":"2020"},{"key":"ref4","article-title":"On the convergence of SGD with biased gradients","volume-title":"Proceedings of Workshop in International Conference on Machine Learning (ICML)","author":"Ajalloeian","year":"2020"},{"key":"ref5","article-title":"Sparsified SGD with memory","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Stich","year":"2018"},{"key":"ref6","article-title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Alistarh","year":"2017"},{"key":"ref7","first-page":"5325","article-title":"Error compensated quantized SGD and its applications to large-scale distributed optimization","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Wu","year":"2018"},{"key":"ref8","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proceedings of Conference in Neural Information Processing Systems (NeurIPS)","author":"Wangni","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3192050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00026"},{"key":"ref12","first-page":"4035","article-title":"ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Zhang","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294915"},{"key":"ref14","article-title":"Distributed learning with compressed gradient differences","author":"Mishchenko","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Adaptive Top-K in SGD for Communication-Efficient Distributed Learning","author":"Ruan","year":"2022","journal-title":"arXiv preprint"}],"event":{"name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","start":{"date-parts":[[2023,12,4]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2023,12,8]]}},"container-title":["GLOBECOM 2023 - 2023 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10436708\/10436716\/10437811.pdf?arnumber=10437811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T01:55:00Z","timestamp":1709258100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10437811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/globecom54140.2023.10437811","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}