{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:27:50Z","timestamp":1774024070338,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"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":[[2023,6,19]]},"DOI":"10.1109\/iwqos57198.2023.10188699","type":"proceedings-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T17:21:00Z","timestamp":1690478460000},"page":"1-10","source":"Crossref","is-referenced-by-count":9,"title":["Boosting Distributed Machine Learning Training Through Loss-tolerant Transmission Protocol"],"prefix":"10.1109","author":[{"given":"Zixuan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]},{"given":"Lei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]},{"given":"Xuandong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]},{"given":"Xin","family":"Ai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]},{"given":"Sen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"Parameter server for distributed machine learning","volume-title":"In Big learning NIPS workshop","volume":"6","author":"Li","year":"2013"},{"key":"ref2","article-title":"Bringing hpc techniques to deep learning","author":"Gibiansky","year":"2017","journal-title":"Baidu Research, Tech. Rep."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1994.1085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2342356.2342390"},{"key":"ref5","first-page":"629","article-title":"Gaia:Geo - Distributed Machine Learning Approaching LAN Speeds","volume-title":"In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Hsieh","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2934002"},{"key":"ref8","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"In Artificial intelligence and statistics","author":"McMahan","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2953793"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986691"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/50.633555"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2002.1019327"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1868447.1868449"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2716281.2836086"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230564"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3243473"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"issue":"30","key":"ref22","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"Alistarh","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3012426.3022184"},{"key":"ref25","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","volume-title":"In International Conference on Learning Representations","author":"Lin","year":"2018"},{"issue":"31","key":"ref26","article-title":"Sparsified sgd with memory","author":"Stich","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"ref29","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref30","volume-title":"NVIDIA. Cuda, release:11.2","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00060"},{"issue":"24","key":"ref32","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent","author":"Recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Quic: A udp-based multiplexed and secure transport","author":"Iyengar","year":"2020","journal-title":"Internet Engineering Task Force, Internet-Draft draft-ietf-quic-transport-27"},{"key":"ref34","volume-title":"Rocev2","author":"Association","year":"2014"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1400097.1400105"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.17487\/rfc3782"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale visual recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"741","article-title":"{ATP}: In-network aggregation for multi-tenant learning","volume-title":"In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Lao","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref40","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5793"},{"key":"ref43","article-title":"8-bit approximations for parallelism in deep learning","author":"Dettmers","year":"2015","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref45","first-page":"6155","article-title":"Doublesqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","volume-title":"In International Conference on Machine Learning","author":"Tang","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3343180.3343186"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.03.006"},{"key":"ref48","article-title":"Scaling distributed machine learning with in-network aggregation","author":"Sapio","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)","location":"Orlando, FL, USA","start":{"date-parts":[[2023,6,19]]},"end":{"date-parts":[[2023,6,21]]}},"container-title":["2023 IEEE\/ACM 31st International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10188660\/10188690\/10188699.pdf?arnumber=10188699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T15:09:11Z","timestamp":1709305751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10188699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iwqos57198.2023.10188699","relation":{},"subject":[],"published":{"date-parts":[[2023,6,19]]}}}