{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T03:40:38Z","timestamp":1769658038867,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322201, U23B2020, 62402525, U22A2028, 92373110"],"award-info":[{"award-number":["62322201, U23B2020, 62402525, U22A2028, 92373110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JKF-2025012343648, JKF-20240598"],"award-info":[{"award-number":["JKF-2025012343648, JKF-20240598"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Complex & Critical Software Environment","award":["SKLCCSE-2025ZX-04"],"award-info":[{"award-number":["SKLCCSE-2025ZX-04"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786440","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"551-563","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ElasGNN: An Elastic Training Framework for Distributed GNN Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0761-3287","authenticated-orcid":false,"given":"Siqi","family":"Wang","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-7927","authenticated-orcid":false,"given":"Hailong","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7197-2873","authenticated-orcid":false,"given":"Pengbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3051-0430","authenticated-orcid":false,"given":"Hongliang","family":"Cao","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7787-6460","authenticated-orcid":false,"given":"Yufan","family":"Xu","sequence":"additional","affiliation":[{"name":"Independent Researcher, Cupertino, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7293-545X","authenticated-orcid":false,"given":"Xuezhu","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-0556","authenticated-orcid":false,"given":"Zhongzhi","family":"Luan","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-2817","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1473","authenticated-orcid":false,"given":"Depei","family":"Qian","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2023. DLRover https:\/\/github.com\/intelligent-machine-learning\/dlrover."},{"key":"e_1_3_2_2_2_1","unstructured":"2023. TorchElastic https:\/\/pytorch.org\/docs\/stable\/distributed.elastic.html."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21144758"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577528"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5400"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Wenqi Fan Yao Ma Qing Li Yuan He Eric Zhao Jiliang Tang and Dawei Yin. 2019. Graph neural networks for social recommendation. In The world wide web conference. 417\u2013426.","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575721"},{"key":"e_1_3_2_2_9_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems, 30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575705"},{"key":"e_1_3_2_2_11_1","volume-title":"Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33 (2020), 22118\u201322133."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650063"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467408"},{"key":"e_1_3_2_2_14_1","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of $Large-Scale$$Multi-Tenant$$GPU$ clusters for $DNN$ training workloads. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). 947\u2013960."},{"key":"e_1_3_2_2_15_1","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with roc","volume":"2","author":"Jia Zhihao","year":"2020","unstructured":"Zhihao Jia, Sina Lin, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2020. Improving the accuracy, scalability, and performance of graph neural networks with roc. Proceedings of Machine Learning and Systems, 2 (2020), 187\u2013198.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_3_2_2_17_1","unstructured":"George Karypis and Vipin Kumar. 1995. Multilevel graph partitioning schemes. In ICPP (3). 113\u2013122."},{"key":"e_1_3_2_2_18_1","volume-title":"METIS: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices.","author":"Karypis George","year":"1997","unstructured":"George Karypis and Vipin Kumar. 1997. METIS: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices."},{"key":"e_1_3_2_2_19_1","volume-title":"Parmetis: Parallel graph partitioning and sparse matrix ordering library.","author":"Karypis George","year":"1997","unstructured":"George Karypis, Kirk Schloegel, and Vipin Kumar. 1997. Parmetis: Parallel graph partitioning and sparse matrix ordering library."},{"key":"e_1_3_2_2_20_1","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607054"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS54959.2023.00062"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_3_2_2_25_1","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Ma Lingxiao","year":"2019","unstructured":"Lingxiao Ma, Zhi Yang, Youshan Miao, Jilong Xue, Ming Wu, Lidong Zhou, and Yafei Dai. 2019. $NeuGraph$: Parallel deep neural network computation on large graphs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). 443\u2013458."},{"key":"e_1_3_2_2_26_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Mai Luo","year":"2020","unstructured":"Luo Mai, Guo Li, Marcel Wagenl\u00e4nder, Konstantinos Fertakis, Andrei-Octavian Brabete, and Peter Pietzuch. 2020. $KungFu$: Making training in distributed machine learning adaptive. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 937\u2013954."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640375"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00035"},{"key":"e_1_3_2_2_29_1","volume-title":"Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing.","author":"Qiao Aurick","year":"2021","unstructured":"Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, and Eric P Xing. 2021. Pollux: Co-adaptive cluster scheduling for goodput-optimized deep learning. In 15th $USENIX$ Symposium on Operating Systems Design and Implementation ($OSDI$ 21)."},{"key":"e_1_3_2_2_30_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Sun Jie","year":"2023","unstructured":"Jie Sun, Li Su, Zuocheng Shi, Wenting Shen, Zeke Wang, Lei Wang, Jie Zhang, Yong Li, Wenyuan Yu, Jingren Zhou, et al. 2023. Legion: Automatically Pushing the Envelope of $Multi-GPU$ System for $Billion-Scale$$GNN$ Training. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 165\u2013179."},{"key":"e_1_3_2_2_31_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903."},{"key":"e_1_3_2_2_32_1","first-page":"5","volume-title":"Proceedings of Machine Learning and Systems","author":"Wan Borui","year":"2023","unstructured":"Borui Wan, Juntao Zhao, and Chuan Wu. 2023. Adaptive message quantization and parallelization for distributed full-graph gnn training. Proceedings of Machine Learning and Systems, 5 (2023)."},{"key":"e_1_3_2_2_33_1","first-page":"673","article-title":"Bns-gcn: Efficient full-graph training of graph convolutional networks with partition-parallelism and random boundary node sampling","volume":"4","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Ang Li, Nam Sung Kim, and Yingyan Lin. 2022. Bns-gcn: Efficient full-graph training of graph convolutional networks with partition-parallelism and random boundary node sampling. Proceedings of Machine Learning and Systems, 4 (2022), 673\u2013693.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_2_34_1","volume-title":"PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In The Tenth International Conference on Learning Representations (ICLR","author":"Wan C","year":"2022","unstructured":"C Wan, Y Li, Cameron R Wolfe, A Kyrillidis, Nam S Kim, and Y Lin. 2022. PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In The Tenth International Conference on Learning Representations (ICLR 2022)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589288"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","unstructured":"Siqi Wang. 2025. PPoPP26_AE_ELASGNN_CODE. https:\/\/doi.org\/10.5281\/zenodo.18143217 Accessed: 2026-01-06 10.5281\/zenodo.18143217","DOI":"10.5281\/zenodo.18143217"},{"key":"e_1_3_2_2_38_1","volume-title":"15th USENIX symposium on operating systems design and implementation (OSDI 21)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. $GNNAdvisor$: An adaptive and efficient runtime system for $GNN$ acceleration on $GPUs$. In 15th USENIX symposium on operating systems design and implementation (OSDI 21). 515\u2013531."},{"key":"e_1_3_2_2_39_1","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Tong Geng, Kevin Barker, Ang Li, and Yufei Ding. 2023. $MGG$: Accelerating graph neural networks with $Fine-Grained$$Intra-Kernel$$Communication-Computation$ pipelining on $Multi-GPU$ platforms. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 779\u2013795."},{"key":"e_1_3_2_2_40_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Weng Qizhen","year":"2022","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, Liping Zhang, Wei Lin, and Yu Ding. 2022. $MLaaS$ in the wild: Workload analysis and scheduling in $Large-Scale$ heterogeneous $GPU$ clusters. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 945\u2013960."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494523"},{"key":"e_1_3_2_2_42_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, et al. 2018. Gandiva: Introspective cluster scheduling for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 595\u2013610."},{"key":"e_1_3_2_2_43_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Xiao Wencong","year":"2020","unstructured":"Wencong Xiao, Shiru Ren, Yong Li, Yang Zhang, Pengyang Hou, Zhi Li, Yihui Feng, Wei Lin, and Yangqing Jia. 2020. $AntMan$: Dynamic scaling on $GPU$ clusters for deep learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 533\u2013548."},{"key":"e_1_3_2_2_44_1","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00083"},{"key":"e_1_3_2_2_46_1","volume-title":"Graphsaint: Graph sampling based inductive learning method. arXiv preprint arXiv:1907.04931.","author":"Zeng Hanqing","year":"2019","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. 2019. Graphsaint: Graph sampling based inductive learning method. arXiv preprint arXiv:1907.04931."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514069"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607056"},{"key":"e_1_3_2_2_51_1","volume-title":"Aligraph: A comprehensive graph neural network platform. arXiv preprint arXiv:1902.08730.","author":"Zhu Rong","year":"2019","unstructured":"Rong Zhu, Kun Zhao, Hongxia Yang, Wei Lin, Chang Zhou, Baole Ai, Yong Li, and Jingren Zhou. 2019. Aligraph: A comprehensive graph neural network platform. arXiv preprint arXiv:1902.08730."}],"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\/3774934.3786440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:27:05Z","timestamp":1769614025000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786440"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":51,"alternative-id":["10.1145\/3774934.3786440","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786440","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"}}]}}