{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:06:24Z","timestamp":1779131184273,"version":"3.51.4"},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"name":"Shandong Provincial Natural Science Foundation of China","award":["ZR2025QC643"],"award-info":[{"award-number":["ZR2025QC643"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62572108"],"award-info":[{"award-number":["62572108"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:p>\n                    Graph Neural Architecture Search (GNAS), a subdomain of Automated Machine Learning (AutoML), aims to automate the design of graph neural network (GNN) architectures. However, GNAS is an inherently data-intensive process, as it calls for the training and evaluation of numerous candidate GNN architectures, leading to massive data access redundancy. Existing multi-GPU GNAS frameworks typically use data parallelism, which incurs high synchronization costs, or architecture parallelism, which struggles to scale to large datasets. We propose\n                    <jats:italic toggle=\"yes\">FastGNAS,<\/jats:italic>\n                    a fast and scalable multi-GPU framework designed to tackle the data management challenges underlying GNAS.First,\n                    <jats:italic toggle=\"yes\">FastGNAS<\/jats:italic>\n                    introduces a hybrid parallel framework that combines data and architecture parallelism, enabled by a novel ring-based model migration. Specifically, it offers an efficient data flow that exploits scalable data parallelism and isolated architecture parallelism to enable synchronization-free processing. Next, to address data redundancy,\n                    <jats:italic toggle=\"yes\">FastGNAS<\/jats:italic>\n                    offers a specialized caching layer for intermediate data products, implemented through advanced batch management strategies including incremental storage and a probabilistic reuse policy. Finally,\n                    <jats:italic toggle=\"yes\">FastGNAS<\/jats:italic>\n                    employs fine-grained load balancing and scheduling via exploratory task generation and predictive workload estimation, enabling purposeful resource allocation across candidate architectures. Extensive experiments show that\n                    <jats:italic toggle=\"yes\">FastGNAS<\/jats:italic>\n                    can accelerate state-of-the-art baselines by an average of 3.14\u00d7 (up to 6.18\u00d7) on diverse benchmarks, while achieving competitive accuracy.\n                  <\/jats:p>","DOI":"10.1145\/3802059","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:16Z","timestamp":1779128356000},"page":"1-27","source":"Crossref","is-referenced-by-count":0,"title":["FastGNAS: Accelerating and Scaling Graph Neural Architecture Search on Multi-GPUs via Ring-Based Model Migration"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8737-2727","authenticated-orcid":false,"given":"Zhen","family":"Song","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7438-894X","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5424-6442","authenticated-orcid":false,"given":"Tianyi","family":"Li","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7422-6254","authenticated-orcid":false,"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3043-3777","authenticated-orcid":false,"given":"Yushuai","family":"Li","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9871-0304","authenticated-orcid":false,"given":"Yanfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9697-7670","authenticated-orcid":false,"given":"Christian S.","family":"Jensen","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8262-8883","authenticated-orcid":false,"given":"Lizhen","family":"Cui","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3171-8889","authenticated-orcid":false,"given":"Ge","family":"Yu","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3749175"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463007"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119617"},{"key":"e_1_2_1_4_1","first-page":"421","article-title":"ClusterEA","author":"Gao Yunjun","year":"2022","unstructured":"Yunjun Gao, Xiaoze Liu, Junyang Wu, Tianyi Li, Pengfei Wang, and Lu Chen. 2022a. ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities. In KDD. 421-431.","journal-title":"In KDD."},{"key":"e_1_2_1_5_1","volume-title":"Graphnas: Graph neural architecture search with reinforcement learning. arXiv:1904.09981","author":"Gao Yang","year":"2019","unstructured":"Yang Gao, Hong Yang, Peng Zhang, Chuan Zhou, and Yue Hu. 2019. Graphnas: Graph neural architecture search with reinforcement learning. arXiv:1904.09981 (2019)."},{"key":"e_1_2_1_6_1","first-page":"6973","article-title":"GraphNAS: Distributed architecture search for graph neural networks","volume":"35","author":"Gao Yang","year":"2022","unstructured":"Yang Gao, Peng Zhang, Hong Yang, Chuan Zhou, Yue Hu, Zhihong Tian, Zhao Li, and Jingren Zhou. 2022b. GraphNAS: Distributed architecture search for graph neural networks. IEEE Transactions on Knowledge and Data Engineering, Vol. 35, 7 (2022), 6973-6987.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617023.3617041"},{"key":"e_1_2_1_8_1","volume-title":"International Conference on Machine Learning. 7968-7981","author":"Guan Chaoyu","year":"2022","unstructured":"Chaoyu Guan, Xin Wang, Hong Chen, Ziwei Zhang, and Wenwu Zhu. 2022. Large-scale graph neural architecture search. In International Conference on Machine Learning. 7968-7981."},{"key":"e_1_2_1_9_1","first-page":"3864","article-title":"Autoattend: Automated attention representation search","author":"Guan Chaoyu","year":"2021","unstructured":"Chaoyu Guan, Xin Wang, and Wenwu Zhu. 2021. Autoattend: Automated attention representation search. In ICML. 3864-3874.","journal-title":"ICML."},{"key":"e_1_2_1_10_1","volume-title":"Inductive representation learning on large graphs. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641217"},{"key":"e_1_2_1_12_1","volume-title":"2021 IEEE 37th International Conference on Data Engineering (ICDE). 552-563","author":"Huan Zhao","year":"2021","unstructured":"Zhao Huan, Yao Quanming, and TU Weiwei. 2021. Search to aggregate neighborhood for graph neural network. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). 552-563."},{"key":"e_1_2_1_13_1","first-page":"615","article-title":"LinE: Logical Query Reasoning over Hierarchical Knowledge Graphs","author":"Huang Zijian","year":"2022","unstructured":"Zijian Huang, Meng-Fen Chiang, and Wang-Chien Lee. 2022. LinE: Logical Query Reasoning over Hierarchical Knowledge Graphs. In KDD. 615-625.","journal-title":"KDD."},{"key":"e_1_2_1_14_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, and Mingyu et al. Gao. 2020. Improving the accuracy, scalability, and performance of graph neural networks with roc. Proceedings of Machine Learning and Systems, Vol. 2 (2020), 187-198.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_1_15_1","volume-title":"Reducing memory contention and i\/o congestion for disk-based gnn training. arXiv:2406.13984","author":"Jiang Qisheng","year":"2024","unstructured":"Qisheng Jiang, Lei Jia, and Chundong Wang. 2024. Reducing memory contention and i\/o congestion for disk-based gnn training. arXiv:2406.13984 (2024)."},{"key":"e_1_2_1_16_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv:1609.02907","author":"Kipf TN","year":"2016","unstructured":"TN Kipf. 2016. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907 (2016)."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3459857"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3459857"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403088"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26026"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3661896"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/3450980.3450987"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3384345.3384353"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63833-7_16"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17033"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649153.3649191"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06379-w"},{"key":"e_1_2_1_29_1","volume-title":"Fgnas: Fpga-aware graph neural architecture search.","author":"Lu Qing","year":"2020","unstructured":"Qing Lu, Weiwen Jiang, Meng Jiang, Jingtong Hu, Sakyasingha Dasgupta, and Yiyu Shi. 2020. Fgnas: Fpga-aware graph neural architecture search. (2020)."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3415089"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681968"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530503"},{"key":"e_1_2_1_33_1","volume-title":"Efficient Mixed Precision Quantization in Graph Neural Networks. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). 4038-4052","author":"Moustafa Samir","year":"2025","unstructured":"Samir Moustafa, Nils Kriege, and Wilfried N Gansterer. 2025. Efficient Mixed Precision Quantization in Graph Neural Networks. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). 4038-4052."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121695"},{"key":"e_1_2_1_35_1","volume-title":"Zaid Quresh, Scott Mahlke, and Wen-mei Hwu.","author":"Park Jeongmin Brian","year":"2024","unstructured":"Jeongmin Brian Park, Kun Wu, Vikram Sharma Mailthody, Zaid Quresh, Scott Mahlke, and Wen-mei Hwu. 2024. Lsm-gnn: Large-scale storage-based multi-gpu gnn training by optimizing data transfer scheme. arXiv:2407.15264 (2024)."},{"key":"e_1_2_1_36_1","volume-title":"Harish Kumar Shakya, and Neeraj Kumar","author":"Singh Shashank Sheshar","year":"2024","unstructured":"Shashank Sheshar Singh, Samya Muhuri, Shivansh Mishra, Divya Srivastava, Harish Kumar Shakya, and Neeraj Kumar. 2024. Social network analysis: A survey on process, tools, and application. ACM computing surveys, Vol. 56, 8 (2024), 1-39."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626716"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00053"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682008"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654990"},{"key":"e_1_2_1_41_1","first-page":"165","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). 165-179."},{"key":"e_1_2_1_42_1","volume-title":"Nam Sung Kim, and Yingyan Lin","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Cameron R Wolfe, Anastasios Kyrillidis, Nam Sung Kim, and Yingyan Lin. 2022. Pipegcn: Efficient full-graph training of graph convolutional networks with pipelined feature communication. arXiv:2203.10428 (2022)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-83090-3"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00044"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657383"},{"key":"e_1_2_1_46_1","first-page":"779","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). 779-795."},{"key":"e_1_2_1_47_1","first-page":"24509","article-title":"Autogel: An automated graph neural network with explicit link information","volume":"34","author":"Wang Zhili","year":"2021","unstructured":"Zhili Wang, Shimin Di, and Lei Chen. 2021. Autogel: An automated graph neural network with explicit link information. Advances in Neural Information Processing Systems, Vol. 34 (2021), 24509-24522.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_48_1","volume-title":"Li","author":"Wu Meng","year":"2025","unstructured":"Meng Wu, Mingyu Yan, and Wenming et al. Li. 2025. Survey on Characterizing and Understanding GNNs From a Computer Architecture Perspective. IEEE Transactions on Parallel and Distributed Systems (2025)."},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3267943"},{"key":"e_1_2_1_50_1","volume-title":"Load balancing in parallel computers: theory and practice","author":"Xu Chenzhong","unstructured":"Chenzhong Xu and Francis CM Lau. 2007. Load balancing in parallel computers: theory and practice. Vol. 381. Springer."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650179"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.27490"},{"key":"e_1_2_1_53_1","volume-title":"AGL: A scalable system for industrial-purpose graph machine learning. arXiv:2003.02454","author":"Zhang Dalong","year":"2020","unstructured":"Dalong Zhang, Xin Huang, Ziqi Liu, Zhiyang Hu, Xianzheng Song, Zhibang Ge, Zhiqiang Zhang, Lin Wang, Jun Zhou, Yang Shuang, et al., 2020. AGL: A scalable system for industrial-purpose graph machine learning. arXiv:2003.02454 (2020)."},{"key":"e_1_2_1_54_1","first-page":"467","article-title":"Understanding gnn computational graph: A coordinated computation, io, and memory perspective","volume":"4","author":"Zhang Hengrui","year":"2022","unstructured":"Hengrui Zhang, Zhongming Yu, Guohao Dai, Guyue Huang, Yufei Ding, Yuan Xie, and Yu Wang. 2022b. Understanding gnn computational graph: A coordinated computation, io, and memory perspective. Proceedings of Machine Learning and Systems, Vol. 4 (2022), 467-484.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Odin Zhang Haitao Lin Xujun Zhang Xiaorui Wang Zhenxing Wu Qing Ye Weibo Zhao Jike Wang Kejun Ying Yu Kang et al. 2025. Graph Neural Networks in Modern AI-aided Drug Discovery. Chemical Reviews (2025).","DOI":"10.1021\/acs.chemrev.5c00461"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511986"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228911"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06383-4"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26338"},{"key":"e_1_2_1_60_1","volume-title":"Simplifying architecture search for graph neural network. arXiv:2008.11652","author":"Zhao Huan","year":"2020","unstructured":"Huan Zhao, Lanning Wei, and Quanming Yao. 2020c. Simplifying architecture search for graph neural network. arXiv:2008.11652 (2020)."},{"key":"e_1_2_1_61_1","volume-title":"Learned low precision graph neural networks. arXiv:2009.09232","author":"Zhao Yiren","year":"2020","unstructured":"Yiren Zhao, Duo Wang, Daniel Bates, Robert Mullins, Mateja Jamnik, and Pietro Lio. 2020a. Learned low precision graph neural networks. arXiv:2009.09232 (2020)."},{"key":"e_1_2_1_62_1","volume-title":"Probabilistic dual network architecture search on graphs. arXiv:2003.09676","author":"Zhao Yiren","year":"2020","unstructured":"Yiren Zhao, Duo Wang, Xitong Gao, Robert Mullins, Pietro Lio, and Mateja Jamnik. 2020b. Probabilistic dual network architecture search on graphs. arXiv:2003.09676 (2020)."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_2_1_64_1","volume-title":"Auto-gnn: Neural architecture search of graph neural networks. Frontiers in big Data","author":"Zhou Kaixiong","year":"2022","unstructured":"Kaixiong Zhou, Xiao Huang, Qingquan Song, Rui Chen, and Xia Hu. 2022. Auto-gnn: Neural architecture search of graph neural networks. Frontiers in big Data, Vol. 5 (2022), 1029307."},{"key":"e_1_2_1_65_1","volume-title":"Aligraph: A comprehensive graph neural network platform. 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:1902.08730 (2019)."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3802059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:22:10Z","timestamp":1779128530000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":65,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,18]]}},"alternative-id":["10.1145\/3802059"],"URL":"https:\/\/doi.org\/10.1145\/3802059","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}