{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T03:41:05Z","timestamp":1769658065509,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786445","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"398-412","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Elastor: Elastic and Efficient Model Partitioning and Checkpointing for Fault-Tolerant Distributed Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4811-5048","authenticated-orcid":false,"given":"Xuanyu","family":"Wang","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1658-0380","authenticated-orcid":false,"given":"Fangcheng","family":"Fu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5342-0194","authenticated-orcid":false,"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3367-7486","authenticated-orcid":false,"given":"Hao","family":"Ge","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1495-0499","authenticated-orcid":false,"given":"Sheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0922-1942","authenticated-orcid":false,"given":"Jiawen","family":"Niu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1681-4677","authenticated-orcid":false,"given":"Bin","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2019. Elastic Horovod. https:\/\/horovod.readthedocs.io\/en\/latest\/elastic_include.html"},{"key":"e_1_3_2_1_2_1","unstructured":"2023. Getting started with Distributed Checkpoint (DCP). https:\/\/pytorch.org\/tutorials\/recipes\/distributed_checkpoint_recipe.html"},{"key":"e_1_3_2_1_3_1","unstructured":"2023. Torch Distributed Elastic. https:\/\/pytorch.org\/docs\/stable\/distributed.elastic.html"},{"key":"e_1_3_2_1_4_1","unstructured":"2024. Dist checkpointing package. https:\/\/docs.nvidia.com\/megatron-core\/developer-guide\/latest\/api-guide\/dist_checkpointing.html"},{"key":"e_1_3_2_1_5_1","unstructured":"2024. Safetensors.. https:\/\/huggingface.co\/docs\/safetensors\/index"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-025-4126-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519584"},{"key":"e_1_3_2_1_8_1","volume-title":"Annual Conference on Neural Information Processing Systems 2020 (NeurIPS","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Annual Conference on Neural Information Processing Systems 2020 (NeurIPS 2020)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716006"},{"key":"e_1_3_2_1_10_1","volume-title":"Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training. CoRR, abs\/2508.00806","author":"Chen Ping","year":"2025","unstructured":"Ping Chen, Zhuohong Deng, Ping Li, Shuibing He, Hongzi Zhu, Yi Zheng, Zhefeng Wang, Baoxing Huai, and Minyi Guo. 2025. Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training. CoRR, abs\/2508.00806 (2025)."},{"key":"e_1_3_2_1_11_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan Damai Dai Daya Guo Dejian Yang Deli Chen Dongjie Ji Erhang Li Fangyun Lin Fucong Dai Fuli Luo Guangbo Hao Guanting Chen Guowei Li H. Zhang Han Bao Hanwei Xu Haocheng Wang Haowei Zhang Honghui Ding Huajian Xin Huazuo Gao Hui Li Hui Qu J. L. Cai Jian Liang Jianzhong Guo Jiaqi Ni Jiashi Li Jiawei Wang Jin Chen Jingchang Chen Jingyang Yuan Junjie Qiu Junlong Li Junxiao Song Kai Dong Kai Hu Kaige Gao Kang Guan Kexin Huang Kuai Yu Lean Wang Lecong Zhang Lei Xu Leyi Xia Liang Zhao Litong Wang Liyue Zhang Meng Li Miaojun Wang Mingchuan Zhang Minghua Zhang Minghui Tang Mingming Li Ning Tian Panpan Huang Peiyi Wang Peng Zhang Qiancheng Wang Qihao Zhu Qinyu Chen Qiushi Du R. J. Chen R. L. Jin Ruiqi Ge Ruisong Zhang Ruizhe Pan Runji Wang Runxin Xu Ruoyu Zhang Ruyi Chen S. S. Li Shanghao Lu Shangyan Zhou Shanhuang Chen Shaoqing Wu Shengfeng Ye Shengfeng Ye Shirong Ma Shiyu Wang Shuang Zhou Shuiping Yu Shunfeng Zhou Shuting Pan T. Wang Tao Yun Tian Pei Tianyu Sun W. L. Xiao and Wangding Zeng. 2024. DeepSeek-V3 Technical Report. CoRR abs\/2412.19437 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2022","author":"Eisenman Assaf","year":"2022","unstructured":"Assaf Eisenman, Kiran Kumar Matam, Steven Ingram, Dheevatsa Mudigere, Raghuraman Krishnamoorthi, Krishnakumar Nair, Misha Smelyanskiy, and Murali Annavaram. 2022. Check-N-Run: a Checkpointing System for Training Deep Learning Recommendation Models. In 19th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2022, Renton, WA, USA, April 4-6, 2022. USENIX Association, 929\u2013943."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503590"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695960"},{"key":"e_1_3_2_1_15_1","volume-title":"Annual Conference on Neural Information Processing Systems 2019 (NeurIPS","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Xu Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. In Annual Conference on Neural Information Processing Systems 2019 (NeurIPS 2019). 103\u2013112."},{"key":"e_1_3_2_1_16_1","volume-title":"Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI","author":"Hwang Changho","year":"2021","unstructured":"Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park. 2021. Elastic Resource Sharing for Distributed Deep Learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 2021). 721\u2013739."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613152"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3342-y"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of Machine Learning and Systems 2019 (MLSys","author":"Jia Zhihao","year":"2019","unstructured":"Zhihao Jia, Matei Zaharia, and Alex Aiken. 2019. Beyond Data and Model Parallelism for Deep Neural Networks. In Proceedings of Machine Learning and Systems 2019 (MLSys 2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks. In 19th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2025","author":"Jiang Yuxuan","year":"2025","unstructured":"Yuxuan Jiang, Ziming Zhou, Boyu Xu, Beijie Liu, Runhui Xu, and Peng Huang. 2025. Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks. In 19th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2025, Boston, MA, USA, July 7-9, 2025. USENIX Association, 313\u2013329."},{"key":"e_1_3_2_1_21_1","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. MegaScale: Scaling Large Language Model Training to More Than 10, 000 GPUs. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 2024). 745\u2013760."},{"key":"e_1_3_2_1_22_1","volume-title":"Scaling Laws for Neural Language Models. CoRR, abs\/2001.08361","author":"Kaplan Jared","year":"2020","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. CoRR, abs\/2001.08361 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations 2015 (ICLR","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations 2015 (ICLR 2015)."},{"key":"e_1_3_2_1_24_1","volume-title":"Reducing Activation Recomputation in Large Transformer Models. CoRR, abs\/2205.05198","author":"Korthikanti Vijay","year":"2022","unstructured":"Vijay Korthikanti, Jared Casper, Sangkug Lym, Lawrence McAfee, Michael Andersch, Mohammad Shoeybi, and Bryan Catanzaro. 2022. Reducing Activation Recomputation in Large Transformer Models. CoRR, abs\/2205.05198 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"Hetu v2: A General and Scalable Deep Learning System with Hierarchical and Heterogeneous Single Program Multiple Data Annotations. CoRR, abs\/2504.20490","author":"Li Haoyang","year":"2025","unstructured":"Haoyang Li, Fangcheng Fu, Hao Ge, Sheng Lin, Xuanyu Wang, Jiawen Niu, Xupeng Miao, and Bin Cui. 2025. Hetu v2: A General and Scalable Deep Learning System with Hierarchical and Heterogeneous Single Program Multiple Data Annotations. CoRR, abs\/2504.20490 (2025)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725322"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587445"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_29_1","volume-title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training. CoRR, abs\/2410.06511","author":"Liang Wanchao","year":"2024","unstructured":"Wanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-Chin Huang, Iris Zhang, Wei Feng, Howard Huang, Junjie Wang, Sanket Purandare, Gokul Nadathur, and Stratos Idreos. 2024. TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training. CoRR, abs\/2410.06511 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources. CoRR, abs\/1904.12043","author":"Lin Haibin","year":"2019","unstructured":"Haibin Lin, Hang Zhang, Yifei Ma, Tong He, Zhi Zhang, Sheng Zha, and Mu Li. 2019. Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources. CoRR, abs\/1904.12043 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations 2019 (ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations 2019 (ICLR 2019)."},{"key":"e_1_3_2_1_32_1","unstructured":"Meta. 2024. Introducing Meta Llama 3: The most capable openly available LLM to date. https:\/\/ai.meta.com\/blog\/meta-llama-3\/"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3570690.3570697"},{"key":"e_1_3_2_1_34_1","volume-title":"Mixed Precision Training. In 6th International Conference on Learning Representations 2018 (ICLR","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory F. Diamos, Erich Elsen, David Garc\u00eda, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed Precision Training. In 6th International Conference on Learning Representations 2018 (ICLR 2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters. In Architectural Support for Programming Languages and Operating Systems 2020 (ASPLOS","author":"Mo Zizhao","year":"2024","unstructured":"Zizhao Mo, Huanle Xu, and Chengzhong Xu. 2024. Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters. In Architectural Support for Programming Languages and Operating Systems 2020 (ASPLOS 2020). 499\u2013513."},{"key":"e_1_3_2_1_36_1","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies, FAST 2021","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies, FAST 2021, February 23-25, 2021. USENIX Association, 203\u2013216."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_38_1","volume-title":"Memory-Efficient Pipeline-Parallel DNN Training. In International Conference on Machine Learning 2021 (ICML","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, and Matei Zaharia. 2021. Memory-Efficient Pipeline-Parallel DNN Training. In International Conference on Machine Learning 2021 (ICML 2021). 139, 7937\u20137947."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of Machine Learning and Systems 2020 (MLSys","author":"Or Andrew","year":"2020","unstructured":"Andrew Or, Haoyu Zhang, and Michael J. Freedman. 2020. Resource Elasticity in Distributed Deep Learning. In Proceedings of Machine Learning and Systems 2020 (MLSys 2020)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_44_1","volume-title":"ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference (ATC","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. ZeRO-Offload: Democratizing Billion-Scale Model Training. In 2021 USENIX Annual Technical Conference (ATC 2021). 551\u2013564."},{"key":"e_1_3_2_1_45_1","volume-title":"Horovod: fast and easy distributed deep learning in TensorFlow. CoRR, abs\/1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: fast and easy distributed deep learning in TensorFlow. CoRR, abs\/1802.05799 (2018)."},{"key":"e_1_3_2_1_46_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR, abs\/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. CoRR, abs\/1909.08053 (2019)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655843"},{"key":"e_1_3_2_1_48_1","volume-title":"Piper: Multidimensional Planner for DNN Parallelization. In Annual Conference on Neural Information Processing Systems 2021 (NeurIPS","author":"Tarnawski Jakub","year":"2021","unstructured":"Jakub Tarnawski, Deepak Narayanan, and Amar Phanishayee. 2021. Piper: Multidimensional Planner for DNN Parallelization. In Annual Conference on Neural Information Processing Systems 2021 (NeurIPS 2021). 24829\u201324840."},{"key":"e_1_3_2_1_49_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","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 2023). 497\u2013513."},{"key":"e_1_3_2_1_50_1","volume-title":"Annual Conference on Neural Information Processing Systems 2017 (NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Annual Conference on Neural Information Processing Systems 2017 (NeurIPS 2017). 5998\u20136008."},{"key":"e_1_3_2_1_51_1","volume-title":"ByteCheckpoint: A Unified Checkpointing System for LLM Development. CoRR, abs\/2407.20143","author":"Wan Borui","year":"2024","unstructured":"Borui Wan, Mingji Han, Yiyao Sheng, Zhichao Lai, Mofan Zhang, Junda Zhang, Yanghua Peng, Haibin Lin, Xin Liu, and Chuan Wu. 2024. ByteCheckpoint: A Unified Checkpointing System for LLM Development. CoRR, abs\/2407.20143 (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"Connor Holmes, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He.","author":"Wang Guanhua","year":"2023","unstructured":"Guanhua Wang, Heyang Qin, Sam Ade Jacobs, Connor Holmes, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He. 2023. ZeRO++: Extremely Efficient Collective Communication for Giant Model Training. CoRR, abs\/2306.10209 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Jie Wang Tianrui Li Yan Yang Shiqian Chen and Wanming Zhai. 2025. DiagLLM: multimodal reasoning with large language model for explainable bearing fault diagnosis. Sci. China Inf. Sci..","DOI":"10.1007\/s11432-024-4333-7"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Min Wang Xiaojie Peng Hongyi Li and Yong He. 2025. Distributed cooperative learning control for multiagent systems with data protection and disturbance observation. Sci. China Inf. Sci..","DOI":"10.1007\/s11432-024-4368-3"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Xin Wang Zirui Chen Haofen Wang Leong Hou U Zhao Li and Wenbin Guo. 2025. Large Language Model Enhanced Knowledge Representation Learning: A Survey. Data Sci. Eng..","DOI":"10.1007\/s41019-025-00285-y"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715998"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_58_1","unstructured":"Weikai Xu Chengrui Huang Shen Gao and Shuo Shang. 2025. LLM-Based Agents for Tool Learning: A Survey. Data Sci. Eng.."},{"key":"e_1_3_2_1_59_1","volume-title":"SkyPilot: An Intercloud Broker for Sky Computing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI","author":"Yang Zongheng","year":"2023","unstructured":"Zongheng Yang, Zhanghao Wu, Michael Luo, Wei-Lin Chiang, Romil Bhardwaj, Woosuk Kwon, Siyuan Zhuang, Frank Sifei Luan, Gautam Mittal, Scott Shenker, and Ion Stoica. 2023. SkyPilot: An Intercloud Broker for Sky Computing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 2023). 437\u2013455."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/3561261.3561265"},{"key":"e_1_3_2_1_61_1","first-page":"3848","article-title":"PyTorch FSDP","volume":"16","author":"Zhao Yanli","year":"2023","unstructured":"Yanli Zhao, Andrew Gu, Rohan Varma, Liang Luo, Chien-Chin Huang, Min Xu, Less Wright, Hamid Shojanazeri, Myle Ott, Sam Shleifer, Alban Desmaison, Can Balioglu, Pritam Damania, Bernard Nguyen, Geeta Chauhan, Yuchen Hao, Ajit Mathews, and Shen Li. 2023. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. Proc. VLDB Endow., 16, 12 (2023), 3848\u20133860.","journal-title":"Experiences on Scaling Fully Sharded Data Parallel. Proc. VLDB Endow."},{"key":"e_1_3_2_1_62_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022). 559\u2013578."}],"event":{"name":"PPoPP '26: 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Sydney NSW Australia","acronym":"PPoPP '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774934.3786445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:27:25Z","timestamp":1769614045000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":62,"alternative-id":["10.1145\/3774934.3786445","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786445","relation":{},"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}