{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:34:07Z","timestamp":1774449247761,"version":"3.50.1"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,2]]},"DOI":"10.1109\/infocom48880.2022.9796752","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:18:49Z","timestamp":1655759929000},"page":"760-769","source":"Crossref","is-referenced-by-count":10,"title":["AutoByte: Automatic Configuration for Optimal Communication Scheduling in DNN Training"],"prefix":"10.1109","author":[{"given":"Yiqing","family":"Ma","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,iSING Lab"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,iSING Lab"}]},{"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University,NICEX Lab"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,iSING Lab"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Scaling distributed machine learning with in-network aggregation","author":"sapio","year":"2021","journal-title":"NSDI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057082"},{"key":"ref32","article-title":"Scaling distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"OSDI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00203"},{"key":"ref30","article-title":"Nsdi","author":"lao","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref36","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref34","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD49709.2020.00014"},{"key":"ref27","article-title":"A unified architecture for accelerating distributed {DNN} training in heterogeneous gpu\/cpu clusters","author":"jiang","year":"2020","journal-title":"OSDI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref2","article-title":"Cherrypick: Adaptively unearthing the best cloud configurations for big data analytics","author":"alipourfard","year":"2017","journal-title":"NSDI"},{"key":"ref1","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref20","first-page":"106622","article-title":"Automl: A survey of the state-of-the-art. Knowledge-Based Systems","volume":"212","author":"he","year":"2021"},{"key":"ref22","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"NeurIPS"},{"key":"ref21","author":"hintjens","year":"2013","journal-title":"Zeromq Messaging for Many Applications"},{"key":"ref24","article-title":"Densenet: Implementing efficient convnet descriptor pyramids","author":"iandola","year":"2014"},{"key":"ref23","article-title":"Gaia: Geo-distributed machine learning approaching {LAN} speeds","author":"hsieh","year":"2017","journal-title":"NSDI"},{"key":"ref26","article-title":"Nccl 2.0","author":"jeaugey","year":"2017","journal-title":"GPU Technology Conference"},{"key":"ref25","article-title":"Priority-based Parameter Propagation for Distributed DNN Training","author":"jayarajan","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934880"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/26.1.73"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/aris.1440370103"},{"key":"ref40","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"simonyan","year":"2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626315"},{"key":"ref13","article-title":"{PCC}: Re-architecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"NSDI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687767"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref16","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"goyal","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"ref18","article-title":"Tictac: Accelerating distributed deep learning with communication scheduling","author":"hashemi","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Information-agnostic flow scheduling for commodity data centers","author":"bai","year":"2015","journal-title":"NSDI"},{"key":"ref3","article-title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Programmable switch as a parallel computing device","author":"chen","year":"2018"},{"key":"ref5","article-title":"A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning","author":"brochu","year":"2010"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2535771.2535788"},{"key":"ref49","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on {GPU} clusters","author":"zhang","year":"2017","journal-title":"ATC"},{"key":"ref9","article-title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","author":"chen","year":"2015"},{"key":"ref46","article-title":"Divide-and-shuffle synchronization for distributed machine learning","author":"wang","year":"2020"},{"key":"ref45","article-title":"Domain-specific communication optimization for distributed dnn training","author":"wang","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3123878.3131975"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343180.3343186"},{"key":"ref42","article-title":"Local sgd converges fast and communicates little","author":"stich","year":"2018"},{"key":"ref41","article-title":"Practical bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3411029.3411037"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2016.7784423"}],"event":{"name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","location":"London, United Kingdom","start":{"date-parts":[[2022,5,2]]},"end":{"date-parts":[[2022,5,5]]}},"container-title":["IEEE INFOCOM 2022 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9796607\/9796652\/09796752.pdf?arnumber=9796752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T20:01:02Z","timestamp":1657569662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9796752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/infocom48880.2022.9796752","relation":{},"subject":[],"published":{"date-parts":[[2022,5,2]]}}}