{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:36:11Z","timestamp":1752982571671,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1109\/noms56928.2023.10154363","type":"proceedings-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T16:50:45Z","timestamp":1687539045000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["Serene: Handling the Effects of Stragglers in In-Network Machine Learning Aggregation"],"prefix":"10.1109","author":[{"given":"Diego Cardoso","family":"Nunes","sequence":"first","affiliation":[{"name":"Federal University of Rio Grande do Sul,Porto Alegre,Brazil"}]},{"given":"Bruno Loureiro","family":"Coelho","sequence":"additional","affiliation":[{"name":"Federal University of Rio Grande do Sul,Porto Alegre,Brazil"}]},{"given":"Ricardo","family":"Parizotto","sequence":"additional","affiliation":[{"name":"Federal University of Rio Grande do Sul,Porto Alegre,Brazil"}]},{"given":"Alberto","family":"Schaeffer-Filho","sequence":"additional","affiliation":[{"name":"Federal University of Rio Grande do Sul,Porto Alegre,Brazil"}]}],"member":"263","reference":[{"key":"ref13","first-page":"693","article-title":"Hogwild! a lock-free approach to parallelizing stochastic gradient descent","author":"niu","year":"2011","journal-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems ser NIPS’11"},{"key":"ref35","article-title":"Libra: In-network gradient aggregation for speeding up distributed sparse deep training","author":"pan","year":"2022","journal-title":"arXiv preprint arXiv 2205 05243"},{"key":"ref12","first-page":"1223","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1 ser NIPS’13"},{"key":"ref34","first-page":"829","article-title":"In-network aggregation for shared machine learning clusters","volume":"3","author":"gebara","year":"2021","journal-title":"Proceedings of Machine Learning and Systems"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.14778\/2777598.2777604"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1145\/3458817.3476178"},{"key":"ref14","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems Volume 2 ser NIPS’15"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1145\/3452296.3472904"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/2987550.2987554"},{"key":"ref30","article-title":"Parallelized Stochastic Gradient Descent","volume":"23","author":"zinkevich","year":"2010","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1145\/2408776.2408794"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/LCOMM.2021.3108940"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/3544216.3544262"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/INFOCOM42981.2021.9488840"},{"key":"ref2","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation ser OSDI’16"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1145\/3377454"},{"key":"ref17","first-page":"371","article-title":"Cetus: Releasing p4 programmers from the chore of trial and error compiling","author":"li","year":"2022","journal-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)"},{"key":"ref39","first-page":"629","article-title":"Gaia:{Geo-Distributed} machine learning approaching {LAN} speeds","author":"hsieh","year":"2017","journal-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)"},{"key":"ref16","article-title":"Efficient data-plane memory scheduling for in-network aggregation","author":"wang","year":"2022","journal-title":"arXiv preprint arXiv 2201 06398"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICDCS.2019.00150"},{"year":"2022","article-title":"Serene repository","key":"ref19"},{"key":"ref18","article-title":"Solving the straggler problem with bounded staleness","author":"cipar","year":"2013","journal-title":"The 14th Workshop on Hot Topics in Operating Systems (HotOS XIV)"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/2534169.2486011"},{"key":"ref23","article-title":"A survey on data plane programming with p4: Fundamentals, advances, and applied research","author":"hauser","year":"2021","journal-title":"arXiv preprint arXiv 2101 10955"},{"key":"ref26","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref25","article-title":"Packet transactions: A programming model for data-plane algorithms at hardware speed","volume":"abs 1512 5023","author":"sivaraman","year":"2015","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/2656877.2656890"},{"key":"ref41","article-title":"Gssp: eliminating stragglers through grouping synchronous for distributed deep learning in heterogeneous cluster","author":"sun","year":"2021","journal-title":"IEEE Transactions on Cloud Computing"},{"year":"2019","article-title":"Npl 1.3 specification","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/2491185.2491190"},{"key":"ref28","first-page":"629","article-title":"Gaia: Geo-distributed machine learning approaching lan speeds","author":"hsieh","year":"2017","journal-title":"Proceedings of the 14th USENIX Conference on Networked Systems Design and Implementation ser NSDI’17"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1006\/jpdc.1994.1085"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1145\/3307650.3322259"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3447868"},{"key":"ref7","first-page":"741","article-title":"{ATP}: In-network aggregation for multi-tenant learning","author":"lao","year":"2021","journal-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/COMHPC.2016.006"},{"key":"ref4","article-title":"Horovod: fast and easy distributed deep learning in tensorflow","author":"sergeev","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1145\/2640087.2644155"},{"key":"ref6","article-title":"Scaling distributed machine learning with in-network aggregation","author":"sapio","year":"2019","journal-title":"arXiv preprint arXiv 1903 06132"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1145\/3152434.3152461"},{"key":"ref40","article-title":"Divide-and-shuffle synchronization for distributed machine learning","volume":"abs 2007 3298","author":"wang","year":"2020","journal-title":"CoRR"}],"event":{"name":"NOMS 2023-2023 IEEE\/IFIP Network Operations and Management Symposium","start":{"date-parts":[[2023,5,8]]},"location":"Miami, FL, USA","end":{"date-parts":[[2023,5,12]]}},"container-title":["NOMS 2023-2023 IEEE\/IFIP Network Operations and Management Symposium"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10154252\/10154208\/10154363.pdf?arnumber=10154363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T17:57:40Z","timestamp":1689011860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10154363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/noms56928.2023.10154363","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]}}}