{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:04:44Z","timestamp":1771329884472,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"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":[[2025,6,8]]},"DOI":"10.1109\/icc52391.2025.11160856","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:34:55Z","timestamp":1758908095000},"page":"5343-5348","source":"Crossref","is-referenced-by-count":1,"title":["Ltfc: Loss-Tolerant Flow Control with RDMA Network for Machine Learning Clusters"],"prefix":"10.1109","author":[{"given":"Yibo","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Qiaojun","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Yiyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Yajie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Yongli","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"CTTL China Academy of Information and Communications Technology,Beijing,China,100191"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.07.078"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref3","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on \\{GPU\\} clusters","volume-title":"2017 USENIX Annual Technical Conference (USENIX ATC 17)","author":"Zhang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303975"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"ref6","first-page":"1","year":"2011","journal-title":"Ieee standard for local and metropolitan area networks-media access control (mac) bridges and virtual bridged local area networksamendment 17: Priority-based flow control,\u201d IEEE Std 802.1Qbb-2011 (Amendment to IEEE Std 802.1Q-2011 as amended by IEEE Std 802.1Qbe-2011 and IEEE Std 802.1Qbc-"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342085"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3375235.3375239"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3336661"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343180.3343186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref16","first-page":"265283","article-title":"\\{TensorFlow\\}: a system for \\{Large-Scale\\} machine learning","volume-title":"in 12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi"},{"key":"ref17","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220636"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"}],"event":{"name":"ICC 2025 - IEEE International Conference on Communications","location":"Montreal, QC, Canada","start":{"date-parts":[[2025,6,8]]},"end":{"date-parts":[[2025,6,12]]}},"container-title":["ICC 2025 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11160703\/11160705\/11160856.pdf?arnumber=11160856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:49:25Z","timestamp":1759243765000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11160856\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icc52391.2025.11160856","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]}}}