{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:27:44Z","timestamp":1786476464384,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":15,"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":"U.S. National Science Foundation (NSF), AI Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE)","award":["2112471"],"award-info":[{"award-number":["2112471"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3828748","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"2057-2059","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward WAN-Aware LLM Training Across Heterogeneous, Geo-Distributed Sites"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1253-8137","authenticated-orcid":false,"given":"Ziyue","family":"Luo","sequence":"first","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4164-6664","authenticated-orcid":false,"given":"Jiaxuan","family":"Cai","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1181-1210","authenticated-orcid":false,"given":"Cedric","family":"Le Denmat","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5761-7730","authenticated-orcid":false,"given":"Srijith","family":"Nair","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2176-5690","authenticated-orcid":false,"given":"Fatemeh","family":"Nourzad","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7767-6143","authenticated-orcid":false,"given":"Rohith Krishnan","family":"Sudha","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5439-6114","authenticated-orcid":false,"given":"Qinhang","family":"Wu","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4707-9088","authenticated-orcid":false,"given":"Jifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison, Madison, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8824-2164","authenticated-orcid":false,"given":"Sungjae","family":"Lee","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4703-4339","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2788-0279","authenticated-orcid":false,"given":"Peiwen","family":"Qiu","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2471-2741","authenticated-orcid":false,"given":"Siddharth","family":"Shah","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5924-1370","authenticated-orcid":false,"given":"Rishabh","family":"Sharma","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison, Madison, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3608-2142","authenticated-orcid":false,"given":"Yinglun","family":"Xia","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0417-0624","authenticated-orcid":false,"given":"Xue","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4894-2501","authenticated-orcid":false,"given":"Zidong","family":"Liu","sequence":"additional","affiliation":[{"name":"ComboCurve, Houston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5246-2982","authenticated-orcid":false,"given":"Bicheng","family":"Ying","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3570-2622","authenticated-orcid":false,"given":"Kaushik","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"The University of Texas Austin, Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6372-9697","authenticated-orcid":false,"given":"Gauri","family":"Joshi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburg, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8635-2992","authenticated-orcid":false,"given":"Yingbin","family":"Liang","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8743-0887","authenticated-orcid":false,"given":"Robert","family":"Nowak","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison, Madison, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6062-6449","authenticated-orcid":false,"given":"Srinivasan","family":"Parthasarathy","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1334-5767","authenticated-orcid":false,"given":"Saurav","family":"Prakash","sequence":"additional","affiliation":[{"name":"Indian Institute Of Technology-Madras, Madras, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5364-7639","authenticated-orcid":false,"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[{"name":"Indian Institute Of Technology-Madras, Madras, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4325-9050","authenticated-orcid":false,"given":"Sanjay","family":"Shakkottai","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4606-6879","authenticated-orcid":false,"given":"Ness B.","family":"Shroff","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5256-9730","authenticated-orcid":false,"given":"Sundararajan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-2728","authenticated-orcid":false,"given":"Haibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0820-3390","authenticated-orcid":false,"given":"Aylin","family":"Yener","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8844-3233","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Arthur Douillard Qixuan Feng Andrei A. Rusu Rachita Chhaparia Yani Donchev Adhiguna Kuncoro Marc'Aurelio Ranzato Arthur Szlam and Jiajun Shen. 2023. DiLoCo: Distributed Low-Communication Training of Language Models. arXiv:2311.08105."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2176"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613152"},{"key":"e_1_3_2_1_4_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arXiv:2001.08361."},{"key":"e_1_3_2_1_5_1","volume-title":"The Thirteenth International Conference on Learning Representations. OpenReview.net","author":"Li Zhe","year":"2025","unstructured":"Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang. 2025. Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization. In The Thirteenth International Conference on Learning Representations. OpenReview.net, Singapore. https:\/\/openreview.net\/forum?id=omrLHFzC37"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"1282","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 54). PMLR, Fort Lauderdale, FL, USA, 1273\u20131282."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR","author":"Nair Srijith","year":"2025","unstructured":"Srijith Nair, Michael Lin, Peizhong Ju, Amirreza Talebi, Elizabeth Serena Bentley, and Jia Liu. 2025. FSL-SAGE: Accelerating Federated Split Learning via Smashed Activation Gradient Estimation. In Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research). PMLR, Vancouver, Canada. https:\/\/openreview.net\/forum?id=HnwcrtoDd4"},{"key":"e_1_3_2_1_8_1","volume-title":"Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning. In Advances in Neural Information Processing Systems 38. Curran Associates","author":"Raje Arian","year":"2025","unstructured":"Arian Raje, Baris Askin, Divyansh Jhunjhunwala, and Gauri Joshi. 2025. Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning. In Advances in Neural Information Processing Systems 38. Curran Associates, Inc., Red Hook, NY, USA. https:\/\/openreview.net\/forum?id=gyn4n8oC9B"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"29440","author":"Ryabinin Max","year":"2023","unstructured":"Max Ryabinin, Tim Dettmers, Michael Diskin, and Alexander Borzunov. 2023. SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202). PMLR, Honolulu, HI, USA, 29416\u201329440."},{"key":"e_1_3_2_1_10_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764839"},{"key":"e_1_3_2_1_12_1","volume-title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23)","author":"Thorpe John","year":"2023","unstructured":"John Thorpe, Pengzhan Zhao, Jonathan Eyolfson, Yifan Qiao, Zhihao Jia, Minjia Zhang, Ravi Netravali, and Guoqing Harry Xu. 2023. Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23). USENIX Association, Boston, MA, USA, 497\u2013513."},{"key":"e_1_3_2_1_13_1","unstructured":"Praneeth Vepakomma Otkrist Gupta Tristan Swedish and Ramesh Raskar. 2018. Split Learning for Health: Distributed Deep Learning Without Sharing Raw Patient Data. arXiv:1812.00564."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_15_1","volume-title":"Towards Building the FederatedGPT: Federated Instruction Tuning. In ICASSP 2024 \u2013 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE","author":"Zhang Jianyi","year":"2024","unstructured":"Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li, Ruiyi Zhang, Tong Yu, Guoyin Wang, and Yiran Chen. 2024. Towards Building the FederatedGPT: Federated Instruction Tuning. In ICASSP 2024 \u2013 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Seoul, Korea, 6915\u20136919."}],"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\/3789240.3828748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:39:19Z","timestamp":1786473559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3828748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":15,"alternative-id":["10.1145\/3789240.3828748","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3828748","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"}}]}}