{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:38:58Z","timestamp":1772933938550,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402098","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"3365-3375","source":"Crossref","is-referenced-by-count":0,"title":["Go With the Flow: Churn-Tolerant Decentralized Training of Large Language Models"],"prefix":"10.1109","author":[{"given":"Nikolay","family":"Blagoev","sequence":"first","affiliation":[{"name":"Worker Thread"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bart","family":"Cox","sequence":"additional","affiliation":[{"name":"Delft University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e9r\u00e9mie","family":"Decouchant","sequence":"additional","affiliation":[{"name":"Delft University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lydia Y.","family":"Chen","sequence":"additional","affiliation":[{"name":"Université de Neuchâtel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pre-training[J]","volume-title":"2025 IEEE International Conference on Big Data (Big Data)","author":"Radford","year":"2018"},{"key":"ref2","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[J]","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","year":"2021"},{"key":"ref3","article-title":"LLaMA: Open and Efficient Foundation Language Models[J]","volume":"abs\/2302.13971","author":"Touvron","year":"2023","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1846"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5498.1903"},{"key":"ref6","article-title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient[J]","volume-title":"International Conference on Machine Learning (ICML)","author":"Ryabinin","year":"2023"},{"key":"ref7","first-page":"1","article-title":"PaLM: Scaling Language Modeling with Pathways[J]","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism[J]","author":"Shoeybi","year":"2019","journal-title":"arXiv: 1909.08053"},{"key":"ref9","article-title":"Attention is All you Need[J]","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","article-title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism[J]","author":"Huang","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref11","first-page":"165","article-title":"Optimal Distributed Online Prediction Using MiniBatches[J]","volume":"13","author":"Dekel","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00040"},{"key":"ref13","article-title":"Asynchronous Decentralized Online Learning[J]","author":"Jiang","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598604"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45748-8_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1982.1675885"},{"key":"ref18","article-title":"In search of an understandable consensus algorithm[J]","volume-title":"USENIX Annual Technical Conference (ATC)","author":"Ongaro","year":"2014"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/0109002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/opre.37.6.865"},{"key":"ref21","volume-title":"Wikimedia Foundation, Wikimedia Downloads","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"ref24","article-title":"Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models[J]","author":"Eisenman","year":"2022","journal-title":"Network and Distributed System Security (NDSI)"},{"key":"ref25","article-title":"As Bitcoin\u2019s Price Surges, Affluent Investors Start to Take a Look[J]","author":"Sullivan","year":"2021","journal-title":"New York Times"},{"key":"ref26","article-title":"A Proof of Useful Work for Artificial Intelligence on the Blockchain[J]","volume":"abs\/2001.09244","author":"Lihu","year":"2020","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref27","first-page":"679","article-title":"DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based Incentive[J]","author":"Weng","year":"2018","journal-title":"IACR Cryptology ePrint Archive"},{"key":"ref28","article-title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing[J]","volume":"abs\/2110.14895","author":"Hu","year":"2021","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref29","article-title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training[J]","volume":"abs\/1806.03377","author":"Harlap","year":"2018","journal-title":"Computing Research Repository (CoRR)"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402098.pdf?arnumber=11402098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:55:47Z","timestamp":1772866547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402098","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}