{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:07:45Z","timestamp":1755907665460,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T00:00:00Z","timestamp":1740700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,28]]},"DOI":"10.1145\/3710848.3710883","type":"proceedings-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T06:20:57Z","timestamp":1740723657000},"page":"29-42","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Parallel Training for Graph Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3176-7816","authenticated-orcid":false,"given":"Kaihao","family":"Ma","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong and AWS Shanghai AI Lab"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4332-2762","authenticated-orcid":false,"given":"Renjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology and AWS Shanghai AI Lab"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-915X","authenticated-orcid":false,"given":"Xiao","family":"Yan","sequence":"additional","affiliation":[{"name":"Centre for Perceptual and Interactive Intelligence and AWS Shanghai AI Lab"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0199-4866","authenticated-orcid":false,"given":"Zhenkun","family":"Cai","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5030-5054","authenticated-orcid":false,"given":"Xiang","family":"Song","sequence":"additional","affiliation":[{"name":"Amazon"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8156-1179","authenticated-orcid":false,"given":"Minjie","family":"Wang","sequence":"additional","affiliation":[{"name":"AWS Shanghai AI Lab"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4657-0901","authenticated-orcid":false,"given":"Yichao","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-6288","authenticated-orcid":false,"given":"James","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,2,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Tensoropt: Exploring the tradeoffs in distributed dnn training with auto-parallelism","author":"Cai Zhenkun","year":"2021","unstructured":"Zhenkun Cai, Xiao Yan, Kaihao Ma, Yidi Wu, Yuzhen Huang, James Cheng, Teng Su, and Fan Yu. 2021. Tensoropt: Exploring the tradeoffs in distributed dnn training with auto-parallelism. IEEE Transactions on Parallel and Distributed Systems (TPDS) (2021), 1967--1981."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577528"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Chen Jie","year":"2018","unstructured":"Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML). 941--949","author":"Chen Jianfei","year":"2018","unstructured":"Jianfei Chen, Jun Zhu, and Le Song. 2018. Stochastic Training of Graph Convolutional Networks with Variance Reduction. In Proceedings of the 35th International Conference on Machine Learning (ICML). 941--949."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Rong Chen Jiaxin Shi Haibo Chen and Binyu Zang. 2015. Bipartite-Oriented Distributed Graph Partitioning for Big Learning. J. Comput. Sci. Technol. (2015) 20--29.","DOI":"10.1007\/s11390-015-1501-x"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Graph library. https:\/\/www.dgl.ai. [Online","author":"DGL.","year":"2023","unstructured":"DGL. 2023. Deep Graph library. https:\/\/www.dgl.ai. [Online; accessed December-2023]."},{"key":"e_1_3_2_1_8_1","volume-title":"DGL Graph Partitioning Tool. https:\/\/docs.dgl.ai\/guide\/distributed-partition.html. [Online","author":"DGL.","year":"2023","unstructured":"DGL. 2023. DGL Graph Partitioning Tool. https:\/\/docs.dgl.ai\/guide\/distributed-partition.html. [Online; accessed December-2023]."},{"volume-title":"Fast Graph Representation Learning with PyTorch Geometric. In ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds.","author":"Fey Matthias","key":"e_1_3_2_1_9_1","unstructured":"Matthias Fey and Jan E. Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR 2019 Workshop on Representation Learning on Graphs and Manifolds."},{"key":"e_1_3_2_1_10_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 551--568","author":"Gandhi Swapnil","year":"2021","unstructured":"Swapnil Gandhi and Anand Padmanabha Iyer. 2021. P3: Distributed deep graph learning at scale. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 551--568."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613168"},{"key":"e_1_3_2_1_12_1","unstructured":"William L. Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems (NeurIPS). 1024--1034."},{"key":"e_1_3_2_1_13_1","volume-title":"Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift. In NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications.","author":"Han Kehang","year":"2021","unstructured":"Kehang Han, Balaji Lakshminarayanan, and Jeremiah Zhe Liu. 2021. Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift. In NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications."},{"key":"e_1_3_2_1_14_1","volume-title":"Yew Soon Ong, and Lu Bai","author":"He Tiantian","year":"2021","unstructured":"Tiantian He, Yew Soon Ong, and Lu Bai. 2021. Learning Conjoint Attentions for Graph Neural Nets. In Advances in Neural Information Processing Systems (NeurIPS). 2641--2653."},{"key":"e_1_3_2_1_15_1","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. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_3_2_1_17_1","unstructured":"Wenbing Huang Tong Zhang Yu Rong and Junzhou Huang. 2018. Adaptive Sampling towards Fast Graph Representation Learning. In Advances in Neural Information Processing Systems (NeurIPS). 4563--4572."},{"key":"e_1_3_2_1_18_1","volume-title":"Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao 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 Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456244"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of Machine Learning and Systems (MLsys). 187--198","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. In Proceedings of Machine Learning and Systems (MLsys). 187--198."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML). 2279--2288","author":"Jia Zhihao","year":"2018","unstructured":"Zhihao Jia, Sina Lin, Charles R Qi, and Alex Aiken. 2018. Exploring Hidden Dimensions in Parallelizing Convolutional Neural Networks.. In Proceedings of the 35th International Conference on Machine Learning (ICML). 2279--2288."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of Machine Learning and Systems (MLsys). 1--13","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 (MLsys). 1--13."},{"key":"e_1_3_2_1_23_1","volume-title":"MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale. arXiv preprint arXiv:2310.12457","author":"Jiang Haitian","year":"2023","unstructured":"Haitian Jiang, Renjie Liu, Xiao Yan, Zhenkun Cai, Minjie Wang, and David Wipf. 2023. MuseGNN: Interpretable and Convergent Graph Neural Network Layers at Scale. arXiv preprint arXiv:2310.12457 (2023)."},{"volume-title":"Encyclopedia of Parallel Computing. 1117--1124.","author":"Karypis George","key":"e_1_3_2_1_24_1","unstructured":"George Karypis. 2011. METIS and ParMETIS. In Encyclopedia of Parallel Computing. 1117--1124."},{"key":"e_1_3_2_1_25_1","series-title":"SIAM J. Sci. Comput. (1998), 359--392","volume-title":"A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs","author":"Karypis George","unstructured":"George Karypis and Vipin Kumar. 1998. A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs. SIAM J. Sci. Comput. (1998), 359--392."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).","author":"Thomas","key":"e_1_3_2_1_27_1","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR)."},{"volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).","author":"Thomas","key":"e_1_3_2_1_28_1","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_3_2_1_31_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI). 103--118","author":"Liu Tianfeng","year":"2023","unstructured":"Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, and Chuanxiong Guo. 2023. BGL: GPU-Efficient GNN Training by Optimizing Graph Data I\/O and Preprocessing. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI). 103--118."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004311"},{"key":"e_1_3_2_1_33_1","unstructured":"Ziqi Liu Zhengwei Wu Zhiqiang Zhang Jun Zhou Shuang Yang Le Song and Yuan Qi. 2020. Bandit Samplers for Training Graph Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_34_1","volume-title":"2019 USENIX Annual Technical Conference (ATC). 443--458","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 (ATC). 443--458."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_37_1","volume-title":"https:\/\/developer.nvidia.com\/cuda-toolkit. [Online","author":"Toolkit NVIDIA.","year":"2023","unstructured":"NVIDIA. 2023. CUDA Toolkit. https:\/\/developer.nvidia.com\/cuda-toolkit. [Online; accessed December-2023]."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00060"},{"key":"e_1_3_2_1_39_1","volume-title":"Seung-Hwan Lim, Hui Guan, and Marco Serafini.","author":"Polisetty Sandeep","year":"2023","unstructured":"Sandeep Polisetty, Juelin Liu, Kobi Falus, Yi Ren Fung, Seung-Hwan Lim, Hui Guan, and Marco Serafini. 2023. GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism. CoRR (2023)."},{"volume-title":"https:\/\/pytorch.org. [Online","year":"2023","key":"e_1_3_2_1_40_1","unstructured":"PyTorch. 2023. PyTroch. https:\/\/pytorch.org. [Online; accessed December-2023]."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469379.3469387"},{"key":"e_1_3_2_1_43_1","volume-title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness. arXiv preprint arXiv:2305.10863","author":"Tan Zeyuan","year":"2023","unstructured":"Zeyuan Tan, Xiulong Yuan, Congjie He, Man-Kit Sit, Guo Li, Xiaoze Liu, Baole Ai, Kai Zeng, Peter Pietzuch, and Luo Mai. 2023. Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness. arXiv preprint arXiv:2305.10863 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Graph clustering with graph neural networks. The Journal of Machine Learning Research","author":"Tsitsulin Anton","year":"2024","unstructured":"Anton Tsitsulin, John Palowitch, Bryan Perozzi, and Emmanuel M\u00fcller. 2024. Graph clustering with graph neural networks. The Journal of Machine Learning Research (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"Graph Attention Networks. In 6th International Conference on Learning Representations (ICLR).","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In 6th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"e_1_3_2_1_47_1","volume-title":"ICLR workshop on representation learning on graphs and manifolds.","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang. 2019. Deep graph library: Towards efficient and scalable deep learning on graphs. In ICLR workshop on representation learning on graphs and manifolds."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303953"},{"key":"e_1_3_2_1_49_1","volume-title":"Defining and Evaluating Network Communities Based on Ground-Truth. In 12th IEEE International Conference on Data Mining (ICDM). IEEE Computer Society, 745--754","author":"Yang Jaewon","year":"2012","unstructured":"Jaewon Yang and Jure Leskovec. 2012. Defining and Evaluating Network Communities Based on Ground-Truth. In 12th IEEE International Conference on Data Mining (ICDM). IEEE Computer Society, 745--754."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"volume-title":"Efficient and Scalable Graph Embedding. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 462--471","author":"Zeng Hanqing","key":"e_1_3_2_1_53_1","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor K. Prasanna. 2019. Accurate, Efficient and Scalable Graph Embedding. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 462--471."},{"key":"e_1_3_2_1_54_1","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link Prediction Based on Graph Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS). 5171--5181."},{"key":"e_1_3_2_1_55_1","unstructured":"Qingru Zhang David Wipf Quan Gan and Le Song. 2021. A Biased Graph Neural Network Sampler with Near-Optimal Regret. In Advances in Neural Information Processing Systems (NeurIPS). 8833--8844."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514069"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_2_1_58_1","volume-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks. Advances in neural information processing systems (NeurIPS)","author":"Zou Difan","year":"2019","unstructured":"Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun, and Quanquan Gu. 2019. Layer-dependent importance sampling for training deep and large graph convolutional networks. Advances in neural information processing systems (NeurIPS) (2019)."}],"event":{"name":"PPoPP '25: The 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Las Vegas NV USA","acronym":"PPoPP '25"},"container-title":["Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3710848.3710883","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3710848.3710883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:16:54Z","timestamp":1755875814000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3710848.3710883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,28]]},"references-count":58,"alternative-id":["10.1145\/3710848.3710883","10.1145\/3710848"],"URL":"https:\/\/doi.org\/10.1145\/3710848.3710883","relation":{},"subject":[],"published":{"date-parts":[[2025,2,28]]},"assertion":[{"value":"2025-02-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}