{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T03:47:08Z","timestamp":1775620028623,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T00:00:00Z","timestamp":1696896000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T00:00:00Z","timestamp":1696896000000},"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":["62132022,61872403,61972421,62302524"],"award-info":[{"award-number":["62132022,61872403,61972421,62302524"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,10]]},"DOI":"10.1109\/icnp59255.2023.10355636","type":"proceedings-article","created":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T19:18:50Z","timestamp":1703099930000},"page":"1-11","source":"Crossref","is-referenced-by-count":6,"title":["PA-ATP: Progress-Aware Transmission Protocol for In-Network Aggregation"],"prefix":"10.1109","author":[{"given":"Zhaoyi","family":"Li","sequence":"first","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Jiawei","family":"Huang","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Changsha University,Changsha,Hunan,China"}]},{"given":"Shengwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Qile","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Yijun","family":"Li","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Jingling","family":"Liu","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Wanchun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]},{"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,Hunan,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Efficient data-plane memory scheduling for in-network aggregation","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"785","article-title":"Ports, and Peter Richtarik. Scaling distributed machine learning with in-network aggregation","volume-title":"Proc. USENIX NSDI","author":"Sapio","year":"2021"},{"key":"ref5","first-page":"741","article-title":"Atp: In-network aggregation for multi-tenant learning","volume-title":"Proc. USENIX NSDI","author":"Lao","year":"2021"},{"key":"ref6","first-page":"829","article-title":"In-network aggre-gation for shared machine learning clusters","volume-title":"Proc. MLSys","author":"Gebara","year":"2021"},{"key":"ref7","first-page":"19","article-title":"Communi-cation efficient distributed machine learning with the parameter server","volume":"27","author":"Li","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Horovod: fast and easy distributed deep learning in tensorflow","author":"Sergeev","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"947","article-title":"Analysis of large-scale multi-tenant gpu clusters for dnn training workloads","volume-title":"Proc. USENIX ATC","author":"Jeon","year":"2019"},{"key":"ref10","first-page":"82","article-title":"Plink: Discovering and exploiting datacenter network locality for efficient cloud-based distributed training","volume-title":"Proc. MLSys","author":"Luo","year":"2020"},{"key":"ref11","article-title":"Hog-wild!: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proceedings of NeurIPS","author":"Recht"},{"key":"ref12","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","volume-title":"Proceedings of NeurIPS","author":"Ho"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref17","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787472"},{"key":"ref19","first-page":"463","article-title":"A unified architecture for accelerating distributed dnn training in heterogeneous gpu\/cpu clusters","volume-title":"Proc. USENIX OSDI","author":"Jiang","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_3"},{"key":"ref23","first-page":"633","article-title":"Swamy Sadashivaiah Renu Kananda, Chang-Hong Wu, and Manya Ghobadi. Using trio: juniper networks programmable chipset-for emerging in-network applications","volume-title":"Proceedings of ACM SIGCOMM","author":"Yang"},{"key":"ref24","first-page":"132","article-title":"Priority-based parameter propagation for distributed dnn training","volume-title":"Proc. MLSys","author":"Jayarajan","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1147\/jrd.2019.2947013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"}],"event":{"name":"2023 IEEE 31st International Conference on Network Protocols (ICNP)","location":"Reykjavik, Iceland","start":{"date-parts":[[2023,10,10]]},"end":{"date-parts":[[2023,10,13]]}},"container-title":["2023 IEEE 31st International Conference on Network Protocols (ICNP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10355566\/10355569\/10355636.pdf?arnumber=10355636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T20:24:21Z","timestamp":1705091061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10355636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,10]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icnp59255.2023.10355636","relation":{},"subject":[],"published":{"date-parts":[[2023,10,10]]}}}