{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:43Z","timestamp":1786476463693,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"The Basic and Frontier Research Project of Pengcheng Laboratory","award":["2025QYB004"],"award-info":[{"award-number":["2025QYB004"]}]},{"name":"National Natural Science Foundation of China (NSFC)","award":["62402012"],"award-info":[{"award-number":["62402012"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3828746","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"2050-2056","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TrainSketch: Collision-Protected Switch Telemetry for Distributed LLM Training Flows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0180-493X","authenticated-orcid":false,"given":"Ao","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, Shenzhen, China"},{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-1828","authenticated-orcid":false,"given":"Zhuochen","family":"Fan","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6381-4026","authenticated-orcid":false,"given":"Kaicheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8533-0035","authenticated-orcid":false,"given":"Zeyu","family":"Luan","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4260-1395","authenticated-orcid":false,"given":"Yong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Shenzhen, China"},{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5995-5908","authenticated-orcid":false,"given":"Kejun","family":"Li","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6071-473X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3718958.3750537"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3772356.3772406"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604827"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672252"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalgor.2003.12.001"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934906"},{"key":"e_1_3_2_1_8_1","first-page":"222","volume-title":"ACM SIGCOMM","author":"Zhang Yinda","year":"2021","unstructured":"Yinda Zhang, Zaoxing Liu, Ruixin Wang, Tong Yang, Jizhou Li, Ruijie Miao, Peng Liu, Ruwen Zhang, and Junchen Jiang. CocoSketch: High-performance sketch-based measurement over arbitrary partial key query. In ACM SIGCOMM, pages 207\u2013222, 2021."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432729"},{"key":"e_1_3_2_1_10_1","first-page":"575","volume-title":"ACM SIGCOMM","author":"Yang Tong","year":"2018","unstructured":"Tong Yang, Jie Jiang, Peng Liu, Qun Huang, Junzhi Gong, Yang Zhou, Rui Miao, Xiaoming Li, and Steve Uhlig. Elastic sketch: Adaptive and fast network-wide measurements. In ACM SIGCOMM, pages 561\u2013575, 2018."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"e_1_3_2_1_12_1","first-page":"109","volume-title":"IEEE ICDE","author":"Fan Zhuochen","year":"2022","unstructured":"Zhuochen Fan, Yinda Zhang, Tong Yang, Mingyi Yan, Gang Wen, Yuhan Wu, Hongze Li, and Bin Cui. PeriodicSketch: Finding periodic items in data streams. In IEEE ICDE, pages 96\u2013109, 2022."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882948"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP.2018.00047"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3063772"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737499"},{"key":"e_1_3_2_1_17_1","first-page":"921","volume-title":"USENIX ATC","author":"Gong Junzhi","year":"2018","unstructured":"Junzhi Gong, Tong Yang, Haowei Zhang, Hao Li, Steve Uhlig, Shigang Chen, Lorna Uden, and Xiaoming Li. HeavyKeeper: An accurate algorithm for finding top-k elephant flows. In USENIX ATC, pages 909\u2013921, 2018."},{"key":"e_1_3_2_1_18_1","first-page":"1572","volume-title":"USENIX NSDI","author":"Sun Haifeng","year":"2024","unstructured":"Haifeng Sun, Qun Huang, Jinbo Sun, Wei Wang, Jiaheng Li, Fuliang Li, Yungang Bao, Xin Yao, and Gong Zhang. AutoSketch: Automatic Sketch-Oriented compiler for query-driven network telemetry. In USENIX NSDI, pages 1551\u20131572, 2024."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672236"},{"key":"e_1_3_2_1_20_1","first-page":"540","volume-title":"USENIX NSDI","author":"Yao Zhiyi","year":"2025","unstructured":"Zhiyi Yao, Pengbo Hu, Congcong Miao, Xuya Jia, Zuning Liang, Yuedong Xu, Chunzhi He, Hao Lu, Mingzhuo Chen, Xiang Li, Zekun He, Yachen Wang, Xianneng Zou, and Junchen Jiang. Holmes: Localizing irregularities in LLM training with mega-scale GPU clusters. In USENIX NSDI, pages 523\u2013540, 2025."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP65844.2025.11192447"},{"key":"e_1_3_2_1_22_1","volume-title":"ACM SIGCOMM (Industrial Demo)","author":"Kim Changhoon","year":"2015","unstructured":"Changhoon Kim, Anirudh Sivaraman, Naga Praveen Katta, Antonin Bas, Advait Dixit, and Lawrence J. Wobker. In-band network telemetry via programmable dataplanes. In ACM SIGCOMM (Industrial Demo), 2015."},{"key":"e_1_3_2_1_23_1","first-page":"371","volume-title":"ACM SIGCOMM","author":"Gupta Arpit","year":"2018","unstructured":"Arpit Gupta, Rob Harrison, Marco Canini, Nick Feamster, Jennifer Rexford, and Walter Willinger. Sonata: Query-driven streaming network telemetry. In ACM SIGCOMM, pages 357\u2013371, 2018."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098829"},{"key":"e_1_3_2_1_25_1","first-page":"324","volume-title":"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 USENIX NSDI, pages 311\u2013324, 2016."},{"key":"e_1_3_2_1_26_1","first-page":"86","volume-title":"USENIX NSDI","author":"Zhang Yinda","year":"2025","unstructured":"Yinda Zhang, Liangcheng Yu, Gianni Antichi, Ran Ben Basat, and Vincent Liu. Enabling silent telemetry data transmission with InvisiFlow. In USENIX NSDI, pages 71\u201386, 2025."},{"key":"e_1_3_2_1_27_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_28_1","first-page":"960","volume-title":"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 USENIX ATC, pages 947\u2013960, 2019."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672239"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759838"},{"key":"e_1_3_2_1_32_1","volume-title":"The CAIDA UCSD anonymized internet traces. https:\/\/www.caida.org\/catalog\/datasets\/passive_dataset\/","author":"CAIDA.","year":"2019","unstructured":"CAIDA. The CAIDA UCSD anonymized internet traces. https:\/\/www.caida.org\/catalog\/datasets\/passive_dataset\/, 2019."}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3828746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:39:27Z","timestamp":1786473567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3828746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":32,"alternative-id":["10.1145\/3789240.3828746","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3828746","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}