{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:06:29Z","timestamp":1774631189707,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)","award":["210487104 - SFB 1053"],"award-info":[{"award-number":["210487104 - SFB 1053"]}]},{"name":"National Key Research & Development (R&D) Plan","award":["2022YFB4501703"],"award-info":[{"award-number":["2022YFB4501703"]}]},{"name":"The Major Key Project of PCL","award":["PCL2022A05"],"award-info":[{"award-number":["PCL2022A05"]}]},{"name":"NSFC","award":["61972158"],"award-info":[{"award-number":["61972158"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645383","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"2826-2835","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["\u03bbGrapher: A Resource-Efficient Serverless System for GNN Serving through Graph Sharing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7543-0180","authenticated-orcid":false,"given":"Haichuan","family":"Hu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8570-1345","authenticated-orcid":false,"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory & Huazhong University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8870-4309","authenticated-orcid":false,"given":"Qiangyu","family":"Pei","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1960-5662","authenticated-orcid":false,"given":"Yongjie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9293-8028","authenticated-orcid":false,"given":"Zichen","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanchang University, Nanchang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7181-6128","authenticated-orcid":false,"given":"Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Alibaba. 2020. graph-learn: An Industrial Graph Neural Network. https:\/\/graph-learn.readthedocs.io\/en\/latest\/index_en.html[Online Accessed 12-Feb-2024]."},{"key":"e_1_3_2_2_2_1","volume-title":"Twitter streaming traces","year":"2017","unstructured":"ArchiveTeam. [n.,d.]. Twitter streaming traces, 2017. https:\/\/github.com\/rickypinci\/BATCH\/tree\/sc2020\/traces[Online Accessed, 12-Feb-2024]."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218751"},{"key":"e_1_3_2_2_4_1","unstructured":"AWS. [n. d.]. AWS Auto Scaling. https:\/\/aws.amazon.com\/cn\/autoscaling\/[Online Accessed 12-Feb-2024]."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1521573113"},{"key":"e_1_3_2_2_6_1","unstructured":"AWS Machine Learning Blog. [n. d.]. Build a GNN-based real-time fraud detection solution using Amazon SageMaker Amazon Neptune and the Deep Graph Library. https:\/\/aws.amazon.com\/cn\/blogs\/machine-learning\/build-a-gnn-based-real-time-fraud-detection-solution-using-amazon-sagemaker-amazon-neptune-and-the-deep-graph-library\/[Online Accessed 12-Feb-2024]."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.10.020"},{"key":"e_1_3_2_2_8_1","volume-title":"The anatomy of a scientific rumor. Scientific reports","author":"Domenico Manlio De","year":"2013","unstructured":"Manlio De Domenico, Antonio Lima, Paul Mougel, and Mirco Musolesi. 2013. The anatomy of a scientific rumor. Scientific reports, Vol. 3, 1 (2013), 2980."},{"key":"e_1_3_2_2_9_1","volume-title":"Sign: Scalable inception graph neural networks. arXiv preprint arXiv:2004.11198","author":"Frasca Fabrizio","year":"2020","unstructured":"Fabrizio Frasca, Emanuele Rossi, Davide Eynard, Ben Chamberlain, Michael Bronstein, and Federico Monti. 2020. Sign: Scalable inception graph neural networks. arXiv preprint arXiv:2004.11198 (2020)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557220"},{"key":"e_1_3_2_2_11_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_3_2_2_12_1","volume-title":"Spreadgnn: Serverless multi-task federated learning for graph neural networks. arXiv preprint arXiv:2106.02743","author":"He Chaoyang","year":"2021","unstructured":"Chaoyang He, Emir Ceyani, Keshav Balasubramanian, Murali Annavaram, and Salman Avestimehr. 2021. Spreadgnn: Serverless multi-task federated learning for graph neural networks. arXiv preprint arXiv:2106.02743 (2021)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10922-014-9307-7"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403142"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921"},{"key":"e_1_3_2_2_16_1","unstructured":"Eric Jonas Johann Schleier-Smith Vikram Sreekanti Chia-Che Tsai Anurag Khandelwal Qifan Pu Vaishaal Shankar Joao Carreira Karl Krauth Neeraja Yadwadkar et al. 2019. Cloud programming simplified: A berkeley view on serverless computing. arXiv preprint arXiv:1902.03383 (2019)."},{"key":"e_1_3_2_2_17_1","volume-title":"GRIP: A graph neural network accelerator architecture","author":"Kiningham Kevin","year":"2022","unstructured":"Kevin Kiningham, Philip Levis, and Christopher R\u00e9. 2022. GRIP: A graph neural network accelerator architecture. IEEE Trans. Comput. (2022)."},{"key":"e_1_3_2_2_18_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_2_19_1","unstructured":"Knative. [n. d.]. Knative is an Open-Source Enterprise-level solution to build Serverless and Event Driven Applications. https:\/\/knative.dev\/ docs\/[Online Accessed 12-Feb-2024] ."},{"key":"e_1_3_2_2_20_1","unstructured":"Kuaishou. [n. d.]. Kuaishou is the video-sharing mobile app. https:\/\/https:\/\/www.kuaishou.com\/en\/[Online Accessed 12-Feb-2024] ."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159729"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0033"},{"key":"e_1_3_2_2_23_1","first-page":"120","article-title":"Pytorch-biggraph: A large scale graph embedding system","volume":"1","author":"Lerer Adam","year":"2019","unstructured":"Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, and Alex Peysakhovich. 2019. Pytorch-biggraph: A large scale graph embedding system. Proceedings of Machine Learning and Systems, Vol. 1 (2019), 120--131.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_2_24_1","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Li Jie","year":"2022","unstructured":"Jie Li, Laiping Zhao, Yanan Yang, Kunlin Zhan, and Keqiu Li. 2022. Tetris: Memory-efficient Serverless Inference through Tensor Sharing. In 2022 USENIX Annual Technical Conference (USENIX ATC 22)."},{"key":"e_1_3_2_2_25_1","unstructured":"Zhuohan Li Lianmin Zheng Yinmin Zhong Vincent Liu Ying Sheng Xin Jin Yanping Huang Zhifeng Chen Hao Zhang Joseph E Gonzalez et al. 2023. AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving. arXiv preprint arXiv:2302.11665 (2023)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557084"},{"key":"e_1_3_2_2_27_1","volume-title":"Demystifying the Cost of Serverless Computing: Towards a Win-Win Deal","author":"Liu Fangming","year":"2023","unstructured":"Fangming Liu and Yipei Niu. 2023. Demystifying the Cost of Serverless Computing: Towards a Win-Win Deal. IEEE Transactions on Parallel and Distributed Systems (2023)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557136"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120157"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2576939"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796705"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.01.043"},{"key":"e_1_3_2_2_35_1","volume-title":"Ngoc Thanh Nguyen, and Dosam Hwang","author":"Phan Huyen Trang","year":"2023","unstructured":"Huyen Trang Phan, Ngoc Thanh Nguyen, and Dosam Hwang. 2023. Fake news detection: A survey of graph neural network methods. Applied Soft Computing (2023), 110235."},{"key":"e_1_3_2_2_36_1","unstructured":"AWS Fargate Pricing. [n. d.]. Serverless Compute Engine--AWS Fargate Pricing--Amazon Web Services. https:\/\/aws.amazon.com\/fargate\/pricing\/[Online Accessed 12-Feb-2024] ."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_2_38_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Thorpe John","year":"2021","unstructured":"John Thorpe, Yifan Qiao, Jonathan Eyolfson, Shen Teng, Guanzhou Hu, Zhihao Jia, Jinliang Wei, Keval Vora, Ravi Netravali, Miryung Kim, et al. 2021. Dorylus: Affordable, Scalable, and Accurate $$GNN$$ Training with Distributed $$CPU$$ Servers and Serverless Threads. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). 495--514."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPDC.2019.00012"},{"key":"e_1_3_2_2_40_1","volume-title":"Anoop S V K K Saladi, and Abhirup Mondal","author":"Virinchi Srinivas","year":"2022","unstructured":"Srinivas Virinchi, Anoop S V K K Saladi, and Abhirup Mondal. 2022. Recommending related products using graph neural networks in directed graphs. In ECML-PKDD 2022. https:\/\/www.amazon.science\/publications\/recommending-related-products-using-graph-neural-networks-in-directed-graphs"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"e_1_3_2_2_42_1","volume-title":"ICLR workshop on representation learning on graphs and manifolds.","author":"Wang Minjie Yu","year":"2019","unstructured":"Minjie Yu 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_2_43_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)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796962"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3494523"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3054656"},{"key":"e_1_3_2_2_48_1","volume-title":"How powerful are graph neural networks? arXiv preprint arXiv:1810.00826","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2005.05.008"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511982"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539415"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514069"},{"key":"e_1_3_2_2_54_1","volume-title":"Accelerating large scale real-time GNN inference using channel pruning. arXiv preprint arXiv:2105.04528","author":"Zhou Hongkuan","year":"2021","unstructured":"Hongkuan Zhou, Ajitesh Srivastava, Hanqing Zeng, Rajgopal Kannan, and Viktor Prasanna. 2021. Accelerating large scale real-time GNN inference using channel pruning. arXiv preprint arXiv:2105.04528 (2021)."},{"key":"e_1_3_2_2_55_1","volume-title":"Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA. In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 1108--1117","author":"Zhou Hongkuan","year":"2022","unstructured":"Hongkuan Zhou, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, and Carl Busart. 2022. Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA. In 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 1108--1117."},{"key":"e_1_3_2_2_56_1","volume-title":"Graph neural networks: A review of methods and applications. AI open","author":"Zhou Jie","year":"2020","unstructured":"Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2020. Graph neural networks: A review of methods and applications. AI open, Vol. 1 (2020), 57--81."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645383","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:30:03Z","timestamp":1755822603000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":56,"alternative-id":["10.1145\/3589334.3645383","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645383","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}