{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:18:05Z","timestamp":1755926285576,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/padsw.2018.8644593","type":"proceedings-article","created":{"date-parts":[[2019,2,21]],"date-time":"2019-02-21T23:23:38Z","timestamp":1550791418000},"page":"739-746","source":"Crossref","is-referenced-by-count":8,"title":["Communication Scheduling Optimization for Distributed Deep Learning Systems"],"prefix":"10.1109","author":[{"given":"Ching-Yuan","family":"Tsai","sequence":"first","affiliation":[]},{"given":"Ching-Chi","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Pangfeng","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jan-Jan","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"3d semantic segmentation with submanifold sparse convolutional networks","author":"graham","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref11","article-title":"A closer look at spatiotemporal convolutions for action recognition","author":"tran","year":"2017","journal-title":"arXiv preprint arXiv 1711 11585"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"ref13","article-title":"Scalable distributed dnn training using commodity gpu cloud computing","author":"strom","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref15","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC.2016.004"},{"key":"ref17","article-title":"Adacomp: Adaptive residual gradient compression for data-parallel distributed training","author":"chen","year":"2017","journal-title":"arXiv preprint arXiv 1712 02679"},{"key":"ref18","article-title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns","author":"seide","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref19","article-title":"Qsgd: Randomized quantization for communication-optimal stochastic gradient descent","author":"alistarh","year":"2016","journal-title":"arXiv preprint arXiv 1610 01292"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882950"},{"key":"ref4","article-title":"Sibyl: A system for large scale supervised machine learning","author":"canini","year":"2012","journal-title":"Technical Talk"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2903743"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1145\/2901318.2901323","article-title":"Geeps: Scalable deep learning on distributed gpus with a gpu-specialized parameter server","author":"cui","year":"2016","journal-title":"Proceedings of the Eleventh European Conference on Computer Systems"},{"key":"ref5","first-page":"583","article-title":"Scaling distributed machine learning with the parameter server","volume":"14","author":"li","year":"2014","journal-title":"OSDI"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"ref7","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.20"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref20","first-page":"1508","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"2","article-title":"Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing","author":"zaharia","year":"2012","journal-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation USENIX Association"},{"journal-title":"Spark mllib","year":"0","key":"ref21"},{"key":"ref24","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2484425.2484427"},{"journal-title":"Petuum A framework for iterative-convergent distributed ml","year":"2013","author":"dai","key":"ref26"},{"key":"ref25","first-page":"2379","article-title":"Fast asynchronous parallel stochastic gradient descent: A lock-free approach with convergence guarantee","author":"zhao","year":"2016","journal-title":"AAAI"}],"event":{"name":"2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)","start":{"date-parts":[[2018,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2018,12,13]]}},"container-title":["2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8635632\/8644527\/08644593.pdf?arnumber=8644593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T08:30:26Z","timestamp":1643272226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8644593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/padsw.2018.8644593","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}