{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:59:29Z","timestamp":1759334369070,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1109\/icc52391.2025.11162041","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:34:55Z","timestamp":1758908095000},"page":"01-07","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Device Placement for Distributed Dnn Training"],"prefix":"10.1109","author":[{"given":"Hong","family":"Wang","sequence":"first","affiliation":[{"name":"Memorial University of Newfoundland,Department of Computer Science,St. John&#x0027;s,NL,Canada"}]},{"given":"Jinhao","family":"Luo","sequence":"additional","affiliation":[{"name":"Memorial University of Newfoundland,Department of Computer Science,St. John&#x0027;s,NL,Canada"}]},{"given":"Kaiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Memorial University of Newfoundland,Department of Computer Science,St. John&#x0027;s,NL,Canada"}]},{"given":"Qiang John","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Calgary,Department of Electrical and Software Engineering,Calgary,AB,Canada"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs\/1409.1556","author":"Simonyan","year":"2014","journal-title":"CoRR"},{"journal-title":"The Llama 3 herd of models","year":"2024","author":"Dubey","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.125"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9839126"},{"key":"ref5","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume":"1","author":"Jia","year":"2019","journal-title":"MLSys"},{"key":"ref6","first-page":"559","article-title":"Alpa: Automating inter- and intra-operator parallelism for distributed deep learning","author":"Zheng","year":"2022","journal-title":"USENIX OSDI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3476132"},{"key":"ref8","first-page":"15451","article-title":"Efficient algorithms for device placement of DNN graph operators","volume":"33","author":"Tarnawski","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","first-page":"739","article-title":"TopoOpt: Co-optimizing network topology and parallelization strategy for distributed training jobs","author":"Wang","year":"2023","journal-title":"USENIX NSDI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432728"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3243261"},{"key":"ref12","first-page":"481","article-title":"Heterogeneity-Aware cluster scheduling policies for deep learning workloads","author":"Narayanan","year":"2020","journal-title":"USENIX OSDI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1985.6312192"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/368996.369025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.25080\/tcwv9851"},{"volume-title":"Gurobi Optimizer Reference Manual","year":"2024","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref19"},{"key":"ref20","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref21","article-title":"Fnet: Mixing tokens with fourier transforms","volume":"abs\/2105.03824","author":"Lee-Thorp","year":"2021","journal-title":"CoRR"}],"event":{"name":"ICC 2025 - IEEE International Conference on Communications","start":{"date-parts":[[2025,6,8]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2025,6,12]]}},"container-title":["ICC 2025 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11160703\/11160705\/11162041.pdf?arnumber=11162041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T14:49:04Z","timestamp":1759243744000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11162041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icc52391.2025.11162041","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]}}}