{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:45:03Z","timestamp":1782798303414,"version":"3.54.5"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007847","name":"Natural Science Foundation of Jilin Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007847","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571695","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Rehabilitating over Recomputing: A Novel Failure Recovery Method for Large Model Training"],"prefix":"10.1109","author":[{"given":"Zichen","family":"Wang","sequence":"first","affiliation":[{"name":"Jilin University,College of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongliang","family":"Li","sequence":"additional","affiliation":[{"name":"Jilin University,College of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"China Telecom Cloud Computing Research Institute,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhewen","family":"Xu","sequence":"additional","affiliation":[{"name":"Jilin University,College of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hairui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Jilin University,College of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Jilin University,College of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Jilin University,High Performance Computing Center,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref3","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref4","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref5","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref7","article-title":"Gpipe: Efficient training of giant neural networks using pipeline parallelism","author":"Huang","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"ref10","article-title":"Flexpipe: Maximizing training efficiency for transformer-based models with variable-length inputs","volume-title":"USENIX Annual Technical Conference (ATC)","author":"Zhao"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476209","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the international conference for high performance computing, networking, storage and analysis (SC)","author":"Narayanan"},{"key":"ref12","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.134"},{"key":"ref14","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref15","article-title":"Fastmoe: A fast mixture-of-expert training system","author":"He","year":"2021"},{"key":"ref16","volume-title":"The llama 3 herd of models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650085"},{"key":"ref19","article-title":"Checkfreq: Frequent, fine-grained dnn checkpointing","volume-title":"USENIX Conference on File and Storage Technologies (FAST)","author":"Mohan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707255"},{"key":"ref21","article-title":"Bloom: A 176b-parameter open-access multilingual language model","author":"Workshop","year":"2022"},{"key":"ref22","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref26","article-title":"Fault tolerance in iterative-convergent machine learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Qiao"},{"key":"ref27","article-title":"Understanding and improving failure tolerant training for deep learning recommendation with partial recovery","volume-title":"Proceedings of Machine Learning and Systems(MLSys)","author":"Maeng"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2953131"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696088"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044666"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00054"},{"key":"ref32","article-title":"Switchmt: An adaptive context switching methodology for scalable multi-task learning in intelligent autonomous agents","author":"Devkota","year":"2025"},{"key":"ref33","article-title":"Time-llm: Time series forecasting by reprogramming large language models","author":"Jin","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551828"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127490"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.107597"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref39","article-title":"The step decay schedule: A near optimal, geometrically decaying learning rate procedure for least squares","author":"Ge","year":"2019","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref40","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/361147.361115"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"issue":"2","key":"ref44","volume-title":"Deep learning","volume":"1","author":"Goodfellow","year":"2016"},{"key":"ref45","volume-title":"Forecasting: principles and practice","author":"Hyndman","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2070(97)00044-7"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571695.pdf?arnumber=11571695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:19:13Z","timestamp":1782796753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571695","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}