{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:44:40Z","timestamp":1782834280719,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132022"],"award-info":[{"award-number":["62132022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019091","name":"Key Research and Development Program of Hunan","doi-asserted-by":"publisher","award":["2022WK2005"],"award-info":[{"award-number":["2022WK2005"]}],"id":[{"id":"10.13039\/501100019091","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Hunan Province, China","award":["2021JJ30867"],"award-info":[{"award-number":["2021JJ30867"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,5,8]]},"DOI":"10.1145\/3552326.3587436","type":"proceedings-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T21:18:51Z","timestamp":1722979131000},"page":"639-653","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":31,"title":["A2TP: Aggregator-aware In-network Aggregation for Multi-tenant Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9677-2368","authenticated-orcid":false,"given":"Zhaoyi","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7578-4490","authenticated-orcid":false,"given":"Jiawei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4335-8742","authenticated-orcid":false,"given":"Yijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3525-0339","authenticated-orcid":false,"given":"Aikun","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2801-125X","authenticated-orcid":false,"given":"Shengwen","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8743-0270","authenticated-orcid":false,"given":"Jingling","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-0480","authenticated-orcid":false,"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. arXiv preprint arXiv:2101.03961","author":"Fedus William","year":"2021","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. arXiv preprint arXiv:2101.03961, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799, 2018."},{"key":"e_1_3_2_1_3_1","first-page":"463","volume-title":"Proc. USENIX OSDI","author":"Jiang Yimin","year":"2020","unstructured":"Yimin Jiang, Yibo Zhu, Chang Lan, Bairen Yi, Yong Cui, and Chuanxiong Guo. A unified architecture for accelerating distributed dnn training in heterogeneous gpu\/cpu clusters. In Proc. USENIX OSDI, pages 463--479, 2020."},{"key":"e_1_3_2_1_4_1","first-page":"785","volume-title":"Proc. USENIX NSDI","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan RK Ports, and Peter Richtarik. Scaling distributed machine learning with in-network aggregation. In Proc. USENIX NSDI, pages 785--808, 2021."},{"key":"e_1_3_2_1_5_1","first-page":"829","volume-title":"Proc. MLSys","author":"Gebara Nadeen","year":"2021","unstructured":"Nadeen Gebara, Manya Ghobadi, and Paolo Costa. In-network aggregation for shared machine learning clusters. In Proc. MLSys, pages 829--844, 2021."},{"key":"e_1_3_2_1_6_1","first-page":"741","volume-title":"Proc. USENIX NSDI","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael Swift. Atp: In-network aggregation for multi-tenant learning. In Proc. USENIX NSDI, pages 741--761, 2021."},{"key":"e_1_3_2_1_7_1","unstructured":"Barefoot networks. https:\/\/barefootnetworks.com\/products\/brieftofino\/."},{"key":"e_1_3_2_1_8_1","first-page":"947","volume-title":"Proc. USENIX ATC","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. Analysis of large-scale multi-tenant gpu clusters for dnn training workloads. In Proc. USENIX ATC, pages 947--960, 2019."},{"key":"e_1_3_2_1_9_1","first-page":"311","volume-title":"Proc. USENIX NSDI","author":"Li Yuliang","year":"2016","unstructured":"Yuliang Li, Rui Miao, Changhoon Kim, and Minlan Yu. Flowradar: A better netflow for data centers. In Proc. USENIX NSDI, pages 311--324, 2016."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472887"},{"key":"e_1_3_2_1_11_1","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume":"27","author":"Li Mu","year":"2014","unstructured":"Mu Li, David G Andersen, Alexander J Smola, and Kai Yu. Communication efficient distributed machine learning with the parameter server. Advances in Neural Information Processing Systems, 27:19--27, 2014.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00607"},{"key":"e_1_3_2_1_13_1","first-page":"185","volume-title":"Proc. USENIX NSDI","author":"Ananthanarayanan Ganesh","year":"2013","unstructured":"Ganesh Ananthanarayanan, Ali Ghodsi, Scott Shenker, and Ion Stoica. Effective straggler mitigation: Attack of the clones. In Proc. USENIX NSDI, pages 185--198, 2013."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"e_1_3_2_1_15_1","first-page":"515","volume-title":"Proc. USENIX OSDI","author":"Zhao Hanyu","year":"2020","unstructured":"Hanyu Zhao, Zhenhua Han, Zhi Yang, Quanlu Zhang, Fan Yang, Lidong Zhou, Mao Yang, Francis CM Lau, Yuqi Wang, Yifan Xiong, et al. Hived: Sharing a gpu cluster for deep learning with guarantees. In Proc. USENIX OSDI, pages 515--532, 2020."},{"key":"e_1_3_2_1_16_1","first-page":"595","volume-title":"Proc. USENIX OSDI","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. Gandiva: Introspective cluster scheduling for deep learning. In Proc. USENIX OSDI, pages 595--610, 2018."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796688"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. MLSys","author":"Luo Liang","year":"2020","unstructured":"Liang Luo, Peter West, Arvind Krishnamurthy, Luis Ceze, and Jacob Nelson. Plink: Discovering and exploiting datacenter network locality for efficient cloud-based distributed training. In Proc. MLSys, 2020."},{"key":"e_1_3_2_1_19_1","volume-title":"nvidia dgx-1","author":"Nvidia","year":"2017","unstructured":"Nvidia, nvidia dgx-1, 2017. http:\/\/www.nvidia.com\/dgx-1."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078591"},{"key":"e_1_3_2_1_21_1","first-page":"295","volume-title":"Proc. SoCC","author":"Suminto Riza O","year":"2017","unstructured":"Riza O Suminto, Cesar A Stuardo, Alexandra Clark, Huan Ke, Tanakorn Leesatapornwongsa, Bo Fu, Daniar H Kurniawan, Vincentius Martin, Maheswara Rao G Uma, and Haryadi S Gunawi. Pbse: A robust path-based speculative execution for degraded-network tail tolerance in data-parallel frameworks. In Proc. SoCC, pages 295--308, 2017."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851192"},{"key":"e_1_3_2_1_23_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_26_1","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky and Geoffrey Hinton. Learning multiple layers of features from tiny images. 2009."},{"key":"e_1_3_2_1_27_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"e_1_3_2_1_30_1","volume-title":"Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410","author":"Jozefowicz Rafal","year":"2016","unstructured":"Rafal Jozefowicz, Oriol Vinyals, Mike Schuster, Noam Shazeer, and Yonghui Wu. Exploring the limits of language modeling. arXiv preprint arXiv:1602.02410, 2016."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50743-5_3"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_35_1","first-page":"132","volume-title":"Proc. MLSys","author":"Jayarajan Anand","year":"2019","unstructured":"Anand Jayarajan, Jinliang Wei, Garth Gibson, Alexandra Fedorova, and Gennady Pekhimenko. Priority-based parameter propagation for distributed dnn training. In Proc. MLSys, pages 132--145, 2019."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"}],"event":{"name":"EuroSys '23: Eighteenth European Conference on Computer Systems","location":"Rome Italy","acronym":"EuroSys '23","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Eighteenth European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3587436","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552326.3587436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:39Z","timestamp":1750178859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552326.3587436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":37,"alternative-id":["10.1145\/3552326.3587436","10.1145\/3552326"],"URL":"https:\/\/doi.org\/10.1145\/3552326.3587436","relation":{},"subject":[],"published":{"date-parts":[[2023,5,8]]},"assertion":[{"value":"2023-05-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}