{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:40:55Z","timestamp":1783039255980,"version":"3.54.6"},"reference-count":156,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101002047"],"award-info":[{"award-number":["101002047"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European High-Performance Computing Joint Undertaking","award":["955513"],"award-info":[{"award-number":["955513"]}]},{"name":"ETH Future Computing Laboratory"},{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["101070141"],"award-info":[{"award-number":["101070141"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3303431","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T19:34:59Z","timestamp":1708630499000},"page":"2584-2606","source":"Crossref","is-referenced-by-count":40,"title":["Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-7916","authenticated-orcid":false,"given":"Maciej","family":"Besta","sequence":"first","affiliation":[{"name":"Department of Computer Science, ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"Department of Computer Science, ETH Zurich, Zürich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04086-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626407002843"},{"key":"ref6","article-title":"The PageRank citation ranking: Bringing order to the web","author":"Page","year":"1999"},{"key":"ref7","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref8","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref9","article-title":"Residual gated graph convnets","author":"Bresson","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781584888215-c25"},{"key":"ref11","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref12","first-page":"443","article-title":"Neugraph: Parallel deep neural network computation on large graphs","volume-title":"Proc. USENIX Conf. Usenix Annu. Tech. Conf.","author":"Ma"},{"key":"ref13","article-title":"GReTA: Hardware optimized graph processing for GNNs","volume-title":"Proc. Workshop Resour.-Constrained Mach. Learn.","author":"Kiningham"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"ref15","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"Ying","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313461"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21236\/ADA604834"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1273442.1250759"},{"key":"ref22","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"Bronstein","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3627816"},{"key":"ref24","article-title":"Theoretical foundations of graph neural networks","author":"Veli\u010dkovi\u0107","year":"2021"},{"key":"ref25","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref26","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761646"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2200\/s01045ed1v01y202009aim046"},{"key":"ref30","article-title":"Dorylus: Affordable, scalable, and accurate GNN training over billion-edge graphs","author":"Thorpe","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2988991"},{"key":"ref33","article-title":"$\\mathsf{MPI}$MPI: A message-passing interface standard. Version 3","year":"2012"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"ref35","first-page":"1150","volume-title":"Models of Computation, Theoretical","author":"Bilardi","year":"2011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00059"},{"key":"ref38","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"Hu","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49487-6_4"},{"key":"ref40","article-title":"METIS\u2013Unstructured graph partitioning and sparse matrix ordering system, version 2.0 (2nd ed.)","author":"Karypis","year":"1995"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3200691.3178504"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3210377.3210393"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2001.925093"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639359"},{"key":"ref45","article-title":"PowerGraph: Distributed graph-parallel computation on natural graphs","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Gonzalez"},{"issue":"2","key":"ref46","first-page":"37","article-title":"An interactive data repository with visual analytics","volume-title":"ACM SIGKDD Explorations Newslett.","volume":"17","author":"Rossi","year":"2016"},{"key":"ref47","article-title":"Adaptive load balancing for parallel GNN training","author":"Su","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530503"},{"key":"ref49","article-title":"Benchmarking graph neural networks","author":"Dwivedi","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"ref51","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zou"},{"key":"ref52","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref53","article-title":"GraphSAINT: Graph sampling based inductive learning method","author":"Zeng","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004311"},{"key":"ref56","article-title":"PIPEGCN: Efficient full-graph training of graph convolutional networks with pipelined feature communication","author":"Wan","year":"2022"},{"key":"ref57","first-page":"673","article-title":"BNS-GCN: Efficient full-graph training of graph convolutional networks with partition-parallelism and random boundary node sampling sampling","volume-title":"Proc. Mach. Learn. Syst.","author":"Wan"},{"key":"ref58","article-title":"Efficient distribution for deep learning on large graphs","author":"Hoang","year":"2021","journal-title":"Proc. Workshop Graph Neural Netw. Syst."},{"key":"ref59","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2018.00058"},{"key":"ref61","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref62","article-title":"Stochastic training of graph convolutional networks with variance reduction","author":"Chen","year":"2017"},{"key":"ref63","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","author":"Chen","year":"2018"},{"key":"ref64","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019"},{"key":"ref65","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/227234.227246"},{"key":"ref67","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"ref68","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref71","article-title":"Attention-based graph neural network for semi-supervised learning","author":"Thekumparampil","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref74","first-page":"3837","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref75","first-page":"1993","article-title":"Diffusion-convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Atwood"},{"key":"ref76","first-page":"13333","article-title":"Diffusion improves graph learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Klicpera"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9491"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"ref80","first-page":"321","article-title":"Learning with local and global consistency","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref81","first-page":"912","article-title":"Semi-supervised learning using Gaussian fields and harmonic functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref82","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Klicpera","year":"2018"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403296"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054830"},{"key":"ref85","first-page":"3077","article-title":"Learning with partially absorbing random walks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/12130.12164"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.32"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441590"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3409964.3461796"},{"key":"ref90","article-title":"Sparse tensor algebra as a parallel programming model","author":"Solomonik","year":"2015"},{"key":"ref91","doi-asserted-by":"crossref","DOI":"10.1145\/3126908.3126971","article-title":"Scaling betweenness centrality using communication-efficient sparse matrix multiplication","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Solomonik"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00013"},{"key":"ref93","first-page":"21","article-title":"Global min-cuts in RNC, and other ramifications of a simple min-cut algorithm","volume-title":"Proc. 4th Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Karger"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(82)90008-6"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.14529\/jsfi140204"},{"key":"ref99","article-title":"One weird trick for parallelizing convolutional neural networks","author":"Krizhevsky","year":"2014"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"},{"key":"ref101","article-title":"Explore mixture of experts in graph neural networks","author":"Zhou","year":"2019"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/289"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-7487-7_7"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3128571"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511986"},{"key":"ref106","article-title":"Marius++: Large-scale training of graph neural networks on a single machine","author":"Waleffe","year":"2022"},{"key":"ref107","article-title":"BGL: GPU-efficient GNN training by optimizing graph data I\/O and preprocessing","author":"Liu","year":"2021"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539177"},{"key":"ref109","article-title":"Sequential aggregation and rematerialization: Distributed full-batch training of graph neural networks on large graphs","author":"Mostafa","year":"2021"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456247"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480858"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/rtas52030.2021.00048"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545082"},{"key":"ref116","first-page":"515","article-title":"GNNAdvisor: An efficient runtime system for GNN acceleration on GPUs","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Wang"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3476886.3477515"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"ref120","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with ROC","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","author":"Jia"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3065737"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00036"},{"key":"ref125","article-title":"GMLP: Building scalable and flexible graph neural networks with feature-message passing","author":"Zhang","year":"2021"},{"key":"ref126","first-page":"1","article-title":"fuseGNN: Accelerating graph convolutional neural network training on GPGPU","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Des.","author":"Chen"},{"key":"ref127","first-page":"551","article-title":"P3: Distributed deep graph learning at scale","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Gandhi"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508408"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00074"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00100"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00075"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415482"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476264"},{"key":"ref134","article-title":"ZIPPER: Exploiting tile-and operator-level parallelism for general and scalable graph neural network acceleration","author":"Zhang","year":"2021"},{"key":"ref135","article-title":"GCNear: A hybrid architecture for efficient GCN training with near-memory processing","author":"Zhou","year":"2021"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586181"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586193"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3079142"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00070"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3077956"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8135-9_6"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2022.3197083"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP49362.2020.00019"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375312"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218751"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00034"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99372-6_7"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref152","first-page":"467","article-title":"Understanding GNN computational graph: A coordinated computation, IO, and memory perspective","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","author":"Zhang"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23397-5_10"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.2172\/1821960"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.2172\/1172915"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10443519.pdf?arnumber=10443519","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:35:32Z","timestamp":1712691332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10443519\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":156,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3303431","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}