{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:34:24Z","timestamp":1762432464749,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,19]]},"DOI":"10.1109\/iwqos61813.2024.10682910","type":"proceedings-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T17:41:00Z","timestamp":1727372460000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["TaLB: Tensor-aware Load Balancing for Distributed DNN Training Acceleration"],"prefix":"10.1109","author":[{"given":"Jinbin","family":"Hu","sequence":"first","affiliation":[{"name":"Changsha University of Science and Technology"}]},{"given":"Yi","family":"He","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology"}]},{"given":"Wangqing","family":"Luo","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology"}]},{"given":"Jiawei","family":"Huang","sequence":"additional","affiliation":[{"name":"Central South University"}]},{"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University"}]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology"}]}],"member":"263","reference":[{"article-title":"Accelerating Neural Recommendation Training with Embedding Scheduling","volume-title":"Proc. USENIX NSDI","author":"Zeng","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488815"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"article-title":"Priority-based parameter propagation for distributed DNN training","volume-title":"Proc. MLSys","author":"Jayarajan","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"article-title":"Tictac: Accelerating distributed deep learning with communication scheduling","volume-title":"Proc. MLSys","author":"Hashemi","key":"ref8"},{"article-title":"Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters","volume-title":"Proc. USENIX ATC","author":"Zhang","key":"ref9"},{"article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Advances in neural information processing systems","author":"Alistarh","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3589288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155282"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098841"},{"article-title":"Let it flow: Resilient asymmetric load balancing with flowlet switching","volume-title":"Proc. USENIX NSDI","author":"Vanini","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098839"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621250"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605617"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6567015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2992"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnet.2024.3366336"},{"key":"ref24","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342065"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587451"},{"article-title":"Gaia: Geo-distributed machine learning approaching LAN speeds","volume-title":"Proc. USENIX NSDI","author":"Hsieh","key":"ref28"},{"article-title":"ATP: In-network Aggregation for Multi-tenant Learning","volume-title":"Proc. USENIX NSDI","author":"Lao","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP59255.2023.10355574"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"article-title":"Information-agnostic flow scheduling for commodity data centers","volume-title":"Proc. USENIX NSDI","author":"Bai","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"article-title":"SRNIC: A scalable architecture for RDMA NICs","volume-title":"Proc. USENIX NSDI","author":"Wang","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018467"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3088276"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3359989.3365426"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2377677.2377711"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155388"}],"event":{"name":"2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)","start":{"date-parts":[[2024,6,19]]},"location":"Guangzhou, China","end":{"date-parts":[[2024,6,21]]}},"container-title":["2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10682818\/10682608\/10682910.pdf?arnumber=10682910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:27:46Z","timestamp":1727461666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iwqos61813.2024.10682910","relation":{},"subject":[],"published":{"date-parts":[[2024,6,19]]}}}