{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:29:15Z","timestamp":1768516155589,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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","award":["62101525,62341113,62021001"],"award-info":[{"award-number":["62101525,62341113,62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323136","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Straggler Dynamic Management for Distributed DNN Training"],"prefix":"10.1109","author":[{"given":"Tiance","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Chai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Tan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenzhi","family":"Yuan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexin","family":"Ju","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyin","family":"Zhu","sequence":"additional","affiliation":[{"name":"H3C Technologies Co., Limited,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems","volume":"1","author":"Dean","year":"2012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref3","author":"Lin","year":"2025","journal-title":"Understanding stragglers in large model training using what-if analysis"},{"key":"ref4","author":"Sergeev","year":"2018","journal-title":"Horovod: fast and easy distributed deep learning in tensorflow"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2847220.2847223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2019.2927558"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103770"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3228733"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737587"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"ref12","first-page":"785","article-title":"Scaling distributed machine learning with In-Network aggregation","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Sapio","year":"2021"},{"key":"ref13","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Lao","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref15","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Gebara","year":"2021"},{"key":"ref16","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Gujarati","year":"2020"},{"key":"ref17","author":"Wang","year":"2022","journal-title":"Efficient data-plane memory scheduling for in-network aggregation"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582037"},{"key":"ref19","author":"Chen","year":"2021","journal-title":"P4com: In-network computation with programmable switches"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3425635"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323136.pdf?arnumber=11323136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:37:56Z","timestamp":1768462676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323136","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}