{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:09:52Z","timestamp":1782450592153,"version":"3.54.5"},"reference-count":140,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61732018"],"award-info":[{"award-number":["61732018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872335"],"award-info":[{"award-number":["61872335"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202451"],"award-info":[{"award-number":["62202451"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Austrian-Chinese Cooperative Research and Development Project [Austrian Research Promotion Agency (FFG) and Chinese Academy of Sciences (CAS)]","doi-asserted-by":"publisher","award":["171111KYSB20200002"],"award-info":[{"award-number":["171111KYSB20200002"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"CAS Project for Young Scientists in Basic Research","doi-asserted-by":"publisher","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"CAS Project for Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/jproc.2023.3337442","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T19:21:23Z","timestamp":1702063283000},"page":"1572-1606","source":"Crossref","is-referenced-by-count":47,"title":["A Comprehensive Survey on Distributed Training of Graph Neural Networks"],"prefix":"10.1109","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8259-4265","authenticated-orcid":false,"given":"Haiyang","family":"Lin","sequence":"first","affiliation":[{"name":"State Key Lab of Processors (SKLP), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6915-955X","authenticated-orcid":false,"given":"Mingyu","family":"Yan","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors (SKLP), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-1685","authenticated-orcid":false,"given":"Xiaochun","family":"Ye","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors (SKLP), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-0908","authenticated-orcid":false,"given":"Dongrui","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors (SKLP), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Nathan, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3146-656X","authenticated-orcid":false,"given":"Wenguang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-1788","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Introduction to Graph Theory","volume":"2","author":"West","year":"2001"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-349-03521-2","volume-title":"Graph Theory With Applications","volume":"290","author":"Bondy","year":"1976"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815478"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"ref5","first-page":"548","article-title":"Learning to discover social circles in ego networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"McAuley"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/75556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref13","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref15","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref16","first-page":"5171","article-title":"Link prediction based on graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref17","first-page":"4438","article-title":"An end-to-end deep learning architecture for graph classification","volume-title":"Proc. 32nd AAAI Conf. Artif. Intell. (AAAI), 30th Innov. Appl. Artif. Intell. (IAAI), 8th AAAI Symp. Educ. Adv. Artif. Intell. (EAAI)","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00075"},{"key":"ref21","first-page":"1957","article-title":"Graph convolutional encoders for syntax-aware neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Bastings"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"issue":"4","key":"ref24","first-page":"5045","article-title":"Memory augmented graph neural networks for sequential recommendation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Ma"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218757"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317838"},{"key":"ref29","author":"Oliver","year":"2020","journal-title":"Traffic Prediction With Advanced Graph Neural Networks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301485"},{"key":"ref31","first-page":"4189","article-title":"Spatial\u2013temporal fusion graph neural networks for traffic flow forecasting","volume-title":"Proc. 34th AAAI Conf. Artif. Intell. (AAAI), 33rd Conf. Innov. Appl. Artif. Intell. (IAAI), 11th Symp. Educ. Adv. Artif. Intell. (EAAI)","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013656"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357820"},{"key":"ref34","first-page":"6530","article-title":"Protein interface prediction using graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fout"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref39","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00074"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-03023-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3135329"},{"key":"ref43","volume-title":"Global Social Media Ranking| Statistic"},{"key":"ref44","first-page":"443","article-title":"Neugraph: Parallel deep neural network computation on large graphs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Ma"},{"key":"ref45","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with ROC","volume-title":"Proc. Mach. Learn. Syst.","author":"Jia"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"ref48","article-title":"MG-GCN: Scalable multi-gpu GCN training framework","author":"Balin","year":"2021","journal-title":"arXiv: 2110.08688"},{"key":"ref49","first-page":"495","article-title":"Dorylus: Affordable, scalable, and accurate GNN training with distributed CPU servers and serverless threads","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implement.","author":"Thorpe"},{"key":"ref50","article-title":"Sequential aggregation and rematerialization: Distributed full-batch training of graph neural networks on large graphs","author":"Mostafa","year":"2021","journal-title":"arXiv:2111.06483"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00036"},{"key":"ref53","article-title":"Learn locally, correct globally: A distributed algorithm for training graph neural networks","author":"Ramezani","year":"2021","journal-title":"arXiv:2111.08202"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"ref55","article-title":"GraphTheta: A distributed graph neural network learning system with flexible training strategy","author":"Liu","year":"2021","journal-title":"arXiv:2104.10569"},{"key":"ref56","article-title":"Accelerating training and inference of graph neural networks with fast sampling and pipelining","author":"Kaler","year":"2021","journal-title":"arXiv:2110.08450"},{"key":"ref57","first-page":"551","article-title":"P3: Distributed deep graph learning at scale","volume-title":"Proc. 15th USENIX Symp. Operat. Syst. Design Implement. (OSDI)","author":"Gandhi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796910"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"ref60","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv: 1806.01261"},{"key":"ref61","article-title":"Machine learning on graphs: A model and comprehensive taxonomy","author":"Chami","year":"2020","journal-title":"arXiv:2005.03675"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/679"},{"key":"ref63","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Velickovic"},{"key":"ref64","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018","journal-title":"arXiv:1810.00826"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref66","volume-title":"Riemannian Manifolds: An Introduction to Curvature","volume":"176","author":"Lee","year":"2006"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403118"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3450316"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00203"},{"key":"ref70","first-page":"2132","article-title":"EEGNN: Edge enhanced graph neural network with a Bayesian nonparametric graph model","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","volume":"206","author":"Liu"},{"key":"ref71","first-page":"1","article-title":"On the bottleneck of graph neural networks and its practical implications","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Alon"},{"key":"ref72","first-page":"1","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Rong"},{"key":"ref73","article-title":"Tackling over-smoothing for general graph convolutional networks","author":"Huang","year":"2020","journal-title":"arXiv:2008.09864"},{"key":"ref74","first-page":"1","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref75","first-page":"4563","article-title":"Adaptive sampling towards fast graph representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref76","first-page":"1","article-title":"Graphsaint: Graph sampling based inductive learning method","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Zeng"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467437"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004311"},{"key":"ref80","first-page":"1114","article-title":"Learning steady-states of iterative algorithms over graphs","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Dai"},{"key":"ref81","first-page":"941","article-title":"Stochastic training of graph convolutional networks with variance reduction","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Chen"},{"key":"ref82","first-page":"11247","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Zou","year":"2019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533429"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00056"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2022.3168067"},{"key":"ref87","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019","journal-title":"arXiv:1903.02428"},{"key":"ref88","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019","journal-title":"arXiv:1909.01315"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358318"},{"issue":"3","key":"ref92","doi-asserted-by":"crossref","first-page":"297","DOI":"10.14778\/3157794.3157799","article-title":"A distributed multi-GPU system for fast graph processing","volume":"11","author":"Jia","year":"2017","journal-title":"Proc. VLDB Endowment"},{"key":"ref93","volume-title":"Cuda C++ Programming Guide"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531467"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173180"},{"issue":"12","key":"ref96","article-title":"Metis\u2014Unstructured graph partitioning and sparse matrix ordering system, version 2.0","volume":"97","author":"Karypis","year":"1995","journal-title":"Appl. Phys. Lett."},{"key":"ref97","first-page":"301","article-title":"Gemini: A computation-centric distributed graph processing system","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Design Implement.","author":"Zhu"},{"key":"ref98","first-page":"37","article-title":"Exploiting bounded staleness to speed up big data analytics","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Cui"},{"key":"ref99","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","volume-title":"Proc. 25th Adv. Neural Inf. Process. Syst.","author":"Recht"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00150"},{"key":"ref101","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref102","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv:1604.06174"},{"key":"ref103","article-title":"Checkmate: Breaking the memory wall with optimal tensor rematerialization","volume-title":"Proc. Mach. Learn. Syst.","author":"Jain"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827595287997"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"ref107","first-page":"17","article-title":"Powergraph: Distributed graph-parallel computation on natural graphs","volume-title":"Proc. 10th USENIX Symp. Operating Syst. Design Implement.","author":"Gonzalez"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503293"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339722"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2009.10129177"},{"issue":"12","key":"ref111","doi-asserted-by":"crossref","first-page":"2813","DOI":"10.14778\/3415478.3415482","article-title":"G3 when graph neural networks meet parallel graph processing systems on GPUs","volume":"13","author":"Liu","year":"2020","journal-title":"Proc. VLDB Endow."},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/1839676.1839694"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.31"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.10.004"},{"key":"ref116","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3207127"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2970395"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2988991"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2022.3198281"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"ref122","article-title":"Understanding GNN computational graph: A coordinated computation, IO, and memory perspective","author":"Zhang","year":"2021","journal-title":"arXiv:2110.09524"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2974843"},{"key":"ref124","first-page":"706","article-title":"ShenTu: Processing multi-trillion edge graphs on millions of cores in seconds","volume-title":"Proc. Int. Conf. for High Perform. Comput., Netw., Storage Anal.","author":"Lin"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/11564126_17"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577487"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3592990"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480858"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482014"},{"issue":"8","key":"ref132","doi-asserted-by":"crossref","first-page":"1572","DOI":"10.14778\/3529337.3529342","article-title":"TGL: A general framework for temporal GNN training onbillion-scale graphs","volume":"15","author":"Zhou","year":"2022","journal-title":"Proc. VLDB Endow."},{"key":"ref133","first-page":"1","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Klicpera"},{"key":"ref134","article-title":"DeeperGCN: All you need to train deeper GCNs","author":"Li","year":"2020","journal-title":"arXiv:2006.07739"},{"key":"ref135","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chen"},{"key":"ref136","article-title":"Edge proposal sets for link prediction","author":"Singh","year":"2021","journal-title":"arXiv:2106.15810"},{"key":"ref137","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref138","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Gilmer"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref140","first-page":"103","article-title":"GPIPE: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/10364627\/10348966.pdf?arnumber=10348966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T18:19:38Z","timestamp":1705169978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10348966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":140,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2023.3337442","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}