{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T16:43:42Z","timestamp":1777999422637,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tkde.2025.3558641","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T18:09:24Z","timestamp":1744135764000},"page":"1-15","source":"Crossref","is-referenced-by-count":3,"title":["Scalable and Load-Balanced Full-Graph GNN Training on Multiple GPUs"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4847-6070","authenticated-orcid":false,"given":"Qiange","family":"Wang","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5798-2282","authenticated-orcid":false,"given":"Yao","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-2053","authenticated-orcid":false,"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8618-4581","authenticated-orcid":false,"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref3","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016"},{"key":"ref4","first-page":"1232","article-title":"Large scale distributed deep networks","volume-title":"Proc. 26th Annu. Conf. Neural Inf. Process. Syst.","author":"Dean"},{"key":"ref5","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183734"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527403"},{"key":"ref8","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref9","article-title":"OGB-LSC: A large-scale challenge for machine learning on graphs","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks 1","author":"Hu"},{"key":"ref10","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref11","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref12","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with ROC","volume-title":"Proc. 3rd Conf. Mach. Learn. Syst.","author":"Jia"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/s0927-0507(05)80121-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827595287997"},{"key":"ref16","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2898361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/3007328.3007331"},{"key":"ref19","article-title":"Gated graph sequence neural networks","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref21","first-page":"443","article-title":"Neugraph: Parallel deep neural network computation on large graphs","volume-title":"Proc. 2019 USENIX Annu. Tech. Conf.","author":"Ma"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"ref24","first-page":"171","article-title":"An experimental comparison of partitioning strategies for distributed graph neural network training","volume-title":"Proc. 28th Int. Conf. Extending Database Technol.","author":"Merkel"},{"key":"ref25","article-title":"Extreme-scale model training for everyone","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14778\/3425879.3425883"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476264"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref29","article-title":"Nvidia collective communication library","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/3538598.3538614"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476205"},{"key":"ref34","first-page":"551","article-title":"ZeRO-Offload: Democratizing billion-scale model training","volume-title":"Proc. 2021 USENIX Annu. Tech. Conf.","author":"Ren"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref36","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref37","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. Implementation","author":"Thorpe"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00074"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556213"},{"key":"ref40","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref41","article-title":"PIPEGCN: Efficient full-graph training of graph convolutional networks with pipelined feature communication","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Wan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3589288"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref44","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","author":"Wang","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3626733"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526134"},{"key":"ref47","article-title":"How powerful are graph neural networks?","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00059"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575725"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.14778\/3648160.3648167"},{"key":"ref52","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Zhang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref54","first-page":"301","article-title":"Gemini: A computation-centric distributed graph processing system","volume-title":"Proc. 12th USENIX Symp. Operating Syst. Des. Implementation","author":"Zhu"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/4358933\/10955266.pdf?arnumber=10955266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:20:15Z","timestamp":1749183615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3558641","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}