{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:14:57Z","timestamp":1780708497379,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"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":[[2024,11,20]]},"DOI":"10.1145\/3698038.3698532","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:32:43Z","timestamp":1731565963000},"page":"36-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Kale: Elastic GPU Scheduling for Online DL Model Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2199-6374","authenticated-orcid":false,"given":"Ziyang","family":"Liu","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6334-4925","authenticated-orcid":false,"given":"Renyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6591-7717","authenticated-orcid":false,"given":"Jin","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Kuaishou Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2101-1302","authenticated-orcid":false,"given":"Weihan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6241-8531","authenticated-orcid":false,"given":"Tianyu","family":"Ye","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-5512","authenticated-orcid":false,"given":"Menghao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3331-8976","authenticated-orcid":false,"given":"Sui","family":"Huang","sequence":"additional","affiliation":[{"name":"Kuaishou Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2631-4979","authenticated-orcid":false,"given":"Jiaming","family":"Huang","sequence":"additional","affiliation":[{"name":"Kuaishou Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3826-8436","authenticated-orcid":false,"given":"Chengru","family":"Song","sequence":"additional","affiliation":[{"name":"Kuaishou Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5475-2728","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5331-3364","authenticated-orcid":false,"given":"Tianyu","family":"Wo","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3473-9703","authenticated-orcid":false,"given":"Chunming","family":"Hu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2020.2995937"},{"key":"e_1_3_2_1_2_1","volume-title":"AWS Auto Scaling Documentation. https:\/\/docs.aws.amazon.com\/autoscaling\/index.html Retrieved","author":"Services Amazon Web","year":"2024","unstructured":"Amazon Web Services. 2024. AWS Auto Scaling Documentation. https:\/\/docs.aws.amazon.com\/autoscaling\/index.html Retrieved June, 2024."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486999"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539234"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671511"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446700"},{"key":"e_1_3_2_1_9_1","volume-title":"Deep retrieval: learning a retrievable structure for large-scale recommendations. arXiv preprint arXiv:2007.07203","author":"Gao Weihao","year":"2020","unstructured":"Weihao Gao, Xiangjun Fan, Chong Wang, Jiankai Sun, Kai Jia, Wenzhi Xiao, Ruofan Ding, Xingyan Bin, Hui Yang, and Xiaobing Liu. 2020. Deep retrieval: learning a retrievable structure for large-scale recommendations. arXiv preprint arXiv:2007.07203 (2020)."},{"key":"e_1_3_2_1_10_1","volume-title":"Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision. arXiv preprint arXiv:2205.11913","author":"Gao Wei","year":"2022","unstructured":"Wei Gao, Qinghao Hu, Zhisheng Ye, Peng Sun, Xiaolin Wang, Yingwei Luo, Tianwei Zhang, and Yonggang Wen. 2022. Deep learning workload scheduling in gpu datacenters: Taxonomy, challenges and vision. arXiv preprint arXiv:2205.11913 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/for.3980040103"},{"key":"e_1_3_2_1_12_1","volume-title":"Google Cloud Load Balancing and Autoscaling. https:\/\/cloud.google.com\/compute\/docs\/load-balancing-and-autoscaling Retrieved","author":"Cloud Google","year":"2024","unstructured":"Google Cloud. 2024. Google Cloud Load Balancing and Autoscaling. https:\/\/cloud.google.com\/compute\/docs\/load-balancing-and-autoscaling Retrieved June, 2024."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-66"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.112"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_16_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park. 2021. Elastic resource sharing for distributed deep learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 721--739."},{"key":"e_1_3_2_1_17_1","volume-title":"Time series analysis: forecasting and control. (No Title)","author":"Jenkins Gwilym M","year":"1976","unstructured":"Gwilym M Jenkins and George EP Box. 1976. Time series analysis: forecasting and control. (No Title) (1976)."},{"key":"e_1_3_2_1_18_1","volume-title":"https:\/\/kubernetes.io\/docs\/tasks\/run-application\/horizontal-pod-autoscale\/ Retrieved","author":"HPA.","year":"2024","unstructured":"Kubernetes. 2024. HPA. https:\/\/kubernetes.io\/docs\/tasks\/run-application\/horizontal-pod-autoscale\/ Retrieved June, 2024."},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/kubernetes.io\/docs\/concepts\/workloads\/autoscaling\/ Retrieved","author":"VPA.","year":"2024","unstructured":"Kubernetes. 2024. VPA. https:\/\/kubernetes.io\/docs\/concepts\/workloads\/autoscaling\/ Retrieved June, 2024."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671514"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3151739"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03596-9_57"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545027"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on learning representations.","author":"Liu Shizhan","year":"2021","unstructured":"Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X Liu, and Schahram Dustdar. 2021. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International conference on learning representations."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563477"},{"key":"e_1_3_2_1_26_1","volume-title":"https:\/\/azure.microsoft.com\/en-us\/features\/autoscale\/ Retrieved","author":"Azure Microsoft","year":"2024","unstructured":"Microsoft Azure. 2024. Azure Autoscale. https:\/\/azure.microsoft.com\/en-us\/features\/autoscale\/ Retrieved June, 2024."},{"key":"e_1_3_2_1_27_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson G. Azzolini Dmytro Dzhulgakov Andrey Mallevich Ilia Cherniavskii Yinghai Lu Raghuraman Krishnamoorthi Ansha Yu Volodymyr Kondratenko Stephanie Pereira Xianjie Chen Wenlin Chen Vijay Rao Bill Jia Liang Xiong and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091 (2019). https:\/\/arxiv.org\/abs\/1906.00091"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494866"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"e_1_3_2_1_31_1","volume-title":"Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing.","author":"Qiao Aurick","year":"2021","unstructured":"Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing. 2021. Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning. In 15th { USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21)."},{"key":"e_1_3_2_1_32_1","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Qiu Haoran","year":"2020","unstructured":"Haoran Qiu, Subho S Banerjee, Saurabh Jha, Zbigniew T Kalbarczyk, and Ravishankar K Iyer. 2020. {FIRM}: An intelligent fine-grained resource management framework for {SLO-Oriented} microservices. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 805--825."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387524"},{"key":"e_1_3_2_1_34_1","volume-title":"Online deep learning: Learning deep neural networks on the fly. arXiv preprint arXiv:1711.03705","author":"Sahoo Doyen","year":"2017","unstructured":"Doyen Sahoo, Quang Pham, Jing Lu, and Steven CH Hoi. 2017. Online deep learning: Learning deep neural networks on the fly. arXiv preprint arXiv:1711.03705 (2017)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08957-4"},{"key":"e_1_3_2_1_36_1","volume-title":"13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16)","author":"Venkataraman Shivaram","year":"2016","unstructured":"Shivaram Venkataraman, Zongheng Yang, Michael Franklin, Benjamin Recht, and Ion Stoica. 2016. Ernest: Efficient performance prediction for {Large-Scale} advanced analytics. In 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16). 363--378."},{"key":"e_1_3_2_1_37_1","volume-title":"international conference on machine learning. PMLR, 3560--3569","author":"Villegas Ruben","year":"2017","unstructured":"Ruben Villegas, Jimei Yang, Yuliang Zou, Sungryull Sohn, Xunyu Lin, and Honglak Lee. 2017. Learning to generate long-term future via hierarchical prediction. In international conference on machine learning. PMLR, 3560--3569."},{"key":"e_1_3_2_1_38_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Wang Zibo","year":"2024","unstructured":"Zibo Wang, Pinghe Li, Chieh-Jan Mike Liang, Feng Wu, and Francis Y Yan. 2024. Autothrottle: A Practical {Bi-Level} Approach to Resource Management for {SLO-Targeted} Microservices. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 149--165."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563469"},{"key":"e_1_3_2_1_40_1","volume-title":"Onenet: Enhancing time series forecasting models under concept drift by online ensembling. Advances in Neural Information Processing Systems 36","author":"Wen Qingsong","year":"2024","unstructured":"Qingsong Wen, Weiqi Chen, Liang Sun, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan, et al. 2024. Onenet: Enhancing time series forecasting models under concept drift by online ensembling. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3064966"},{"key":"e_1_3_2_1_42_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. 2018. Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 595--610."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00018"},{"key":"e_1_3_2_1_44_1","volume-title":"SS-LSTM: A hierarchical LSTM model for pedestrian trajectory prediction. In 2018 IEEE winter conference on applications of computer vision (WACV)","author":"Xue Hao","unstructured":"Hao Xue, Du Q Huynh, and Mark Reynolds. 2018. SS-LSTM: A hierarchical LSTM model for pedestrian trajectory prediction. In 2018 IEEE winter conference on applications of computer vision (WACV). IEEE, 1186--1194."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3136245"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"e_1_3_2_1_48_1","volume-title":"A review of recurrent neural networks: LSTM cells and network architectures. Neural computation 31, 7","author":"Yu Yong","year":"2019","unstructured":"Yong Yu, Xiaosheng Si, Changhua Hu, and Jianxun Zhang. 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation 31, 7 (2019), 1235--1270."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671570"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_2_1_54_1","volume-title":"International conference on machine learning. PMLR, 27268--27286","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International conference on machine learning. PMLR, 27268--27286."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3202493"}],"event":{"name":"SoCC '24: ACM Symposium on Cloud Computing","location":"Redmond WA USA","acronym":"SoCC '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698532","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698038.3698532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:57:53Z","timestamp":1755889073000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698038.3698532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":55,"alternative-id":["10.1145\/3698038.3698532","10.1145\/3698038"],"URL":"https:\/\/doi.org\/10.1145\/3698038.3698532","relation":{},"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"2024-11-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}