{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T01:20:11Z","timestamp":1776993611994,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3573037","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"1148-1151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["ElasticDL: A Kubernetes-native Deep Learning Framework with Fault-tolerance and Elastic Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6033-6102","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"first","affiliation":[{"name":"Zhejiang University &amp; Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1228-5843","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4200-0423","authenticated-orcid":false,"given":"Feng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5893-8761","authenticated-orcid":false,"given":"Qitao","family":"Shi","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9795-4158","authenticated-orcid":false,"given":"Wenjing","family":"Fang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9594-3989","authenticated-orcid":false,"given":"Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9011-9758","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Edmundo RM Madeira","author":"Bittencourt Luiz F","year":"2018","unstructured":"Luiz F Bittencourt, Alfredo Goldman, Edmundo RM Madeira, Nelson LS da Fonseca, and Rizos Sakellariou. 2018. Scheduling in distributed systems: A cloud computing perspective. Computer science review, Vol. 30 (2018), 31--54."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Heng-Tze Cheng Levent Koc Jeremiah Harmsen Tal Shaked Tushar Chandra Hrishi Aradhye Glen Anderson Greg Corrado Wei Chai Mustafa Ispir et al. 2016. Wide & deep learning for recommender systems. In DLRS. 7--10.","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_4_1","unstructured":"The Horovod Contributors. 2022a. Horovod Elastic. https:\/\/horovod.readthedocs.io\/en\/stable\/elastic_include.html\/ Last accessed on 2022-06--25."},{"key":"e_1_3_2_1_5_1","unstructured":"The PyTorch Contributors. 2022b. PyTorch Elastic. https:\/\/pytorch.org\/docs\/stable\/distributed.elastic.html\/ Last accessed on 2022-06--26."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.12.001"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.295"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.2885"},{"key":"e_1_3_2_1_9_1","volume-title":"Aryl: An Elastic Cluster Scheduler for Deep Learning. arXiv preprint arXiv:2202.07896","author":"Li Jiamin","year":"2022","unstructured":"Jiamin Li, Hong Xu, and et.al. 2022. Aryl: An Elastic Cluster Scheduler for Deep Learning. arXiv preprint arXiv:2202.07896 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Jianxun Lian Xiaohuan Zhou and et.al. 2018. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In SIGKDD. 1754--1763.","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_1_11_1","volume-title":"A survey of transformers. arXiv preprint arXiv:2106.04554","author":"Lin Tianyang","year":"2021","unstructured":"Tianyang Lin, Yuxin Wang, Xiangyang Liu, and Xipeng Qiu. 2021. A survey of transformers. arXiv preprint arXiv:2106.04554 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"CSUR","volume":"53","author":"Mayer Ruben","year":"2020","unstructured":"Ruben Mayer and Hans-Arno Jacobsen. 2020. Scalable deep learning on distributed infrastructures: Challenges, techniques, and tools. CSUR, Vol. 53, 1 (2020), 1--37."},{"key":"e_1_3_2_1_13_1","volume-title":"Evaluation of gang scheduling performance and cost in a cloud computing system. The journal of supercomputing","author":"Moschakis Ioannis A","year":"2012","unstructured":"Ioannis A Moschakis and Helen D Karatza. 2012. Evaluation of gang scheduling performance and cost in a cloud computing system. The journal of supercomputing, Vol. 59, 2 (2012), 975--992."},{"key":"e_1_3_2_1_14_1","first-page":"400","article-title":"Resource elasticity in distributed deep learning","volume":"2","author":"Or Andrew","year":"2020","unstructured":"Andrew Or, Haoyu Zhang, and Michael Freedman. 2020. Resource elasticity in distributed deep learning. MLSys, Vol. 2 (2020), 400--411.","journal-title":"MLSys"},{"key":"e_1_3_2_1_15_1","volume-title":"Litz: Elastic Framework for $$High-Performance$$ Distributed Machine Learning. In USENIX ATC. 631--644.","author":"Qiao Aurick","year":"2018","unstructured":"Aurick Qiao, Abutalib Aghayev, Weiren Yu, Haoyang Chen, Qirong Ho, Garth A Gibson, and Eric P Xing. 2018. Litz: Elastic Framework for $$High-Performance$$ Distributed Machine Learning. In USENIX ATC. 631--644."},{"key":"e_1_3_2_1_16_1","unstructured":"Matei Zaharia Mosharaf Chowdhury Tathagata Das Ankur Dave Justin Ma Murphy McCauly Michael J Franklin Scott Shenker and Ion Stoica. 2012. Resilient distributed datasets: A $$Fault-Tolerant$$ abstraction for $$In-Memory$$ cluster computing. In NSDI. 15--28."},{"key":"e_1_3_2_1_17_1","volume-title":"when finance meets trustworthy AI. Frontiers of Information Technology & Electronic Engineering","author":"Zhou Jun","year":"2022","unstructured":"Jun Zhou, Chaochao Chen, Longfei Li, Zhiqiang Zhang, and Xiaolin Zheng. 2022. FinBrain 2.0: when finance meets trustworthy AI. Frontiers of Information Technology & Electronic Engineering (2022), 1--18."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098029"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","location":"Singapore Singapore","acronym":"WSDM '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3573037","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3573037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:39Z","timestamp":1750182699000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3573037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":18,"alternative-id":["10.1145\/3539597.3573037","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3573037","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}