{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:14:05Z","timestamp":1772694845733,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"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":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408524","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-16","source":"Crossref","is-referenced-by-count":0,"title":["VeloxGNN: Efficient Out-of-Core GNN Training with Delayed Gradient Propagation"],"prefix":"10.1109","author":[{"given":"Yi","family":"Li","sequence":"first","affiliation":[{"name":"The University of Texas at Dallas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsun-Yu","family":"Yang","sequence":"additional","affiliation":[{"name":"Duke University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoyan","family":"Shen","sequence":"additional","affiliation":[{"name":"Shandong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Chang","family":"Yang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingzhe","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Texas at Dallas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375307"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref5","article-title":"Distributed graph neural network training with periodic stale representation synchronization","author":"Chai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Fastgcn: fast learning with graph convolutional networks via importance sampling","author":"Chen","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Gnnpipe: Accelerating distributed fullgraph gnn training with pipelined model parallelism","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824077"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.44"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0345"},{"key":"ref11","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"in ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey","year":"2019"},{"key":"ref12","first-page":"3294","article-title":"Gnnautoscale: Scalable and expressive graph neural networks via historical embeddings","volume-title":"International conference on machine learning","author":"Fey","year":"2021"},{"key":"ref13","first-page":"551","article-title":"P3: Distributed deep graph learning at scale","volume-title":"15th \\{USENIX\\} Symposium on Operating Systems Design and Implementation (\\{OSDI\\} 21)","author":"Gandhi","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36736-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2986316"},{"key":"ref16","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Ogb-lsc: A large-scale challenge for machine learning on graphs","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"22 118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0812"},{"key":"ref20","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with roc","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Jia","year":"2020"},{"key":"ref21","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proceedings of Machine Learning and Systems","volume":"1","author":"Jia","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"ref25","first-page":"147","article-title":"\\{Hardware\/Software\\}\\{CoProgrammable\\} framework for computational \\{SSDs\\} to accelerate deep learning service on \\{Large-Scale\\} graphs","volume-title":"20th USENIX Conference on File and Storage Technologies (FAST 22)","author":"Kwon","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527391"},{"key":"ref28","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"International conference on machinelearning","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3001531"},{"key":"ref30","article-title":"You only spectralize once: Taking a spectral detour to accelerate graph neural network","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"ref34","first-page":"533","article-title":"Marius: Learning massive graph embeddings on a single machine","volume-title":"15th \\{USENIX\\} Symposium on Operating Systems Design and Implementation (\\{OSDI\\} 21)","author":"Mohoney","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551819"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551819"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/info14020085"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac759"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681976"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339722"},{"key":"ref41","first-page":"495","article-title":"Dorylus: Affordable, scalable, and accurate $\\{\\text{GNN}\\}$ training with distributed CPU servers and serverless threads","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Thorpe"},{"key":"ref42","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107x","year":"2017","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567501"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref45","article-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks","author":"Wang","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526134"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00033"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3340404"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570406"},{"key":"ref50","first-page":"19665","article-title":"Decoupling the depth and scope of graph neural networks","volume":"34","author":"Zeng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"Rethinking the expressive power of gnns via graph biconnectivity","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref53","first-page":"375","article-title":"Gridgraph:large-scale graph processing on a single machine using 2-level hierarchical partitioning","volume-title":"2015 USENIX Annual Technical Conference (USENIX ATC 15)","author":"Zhu","year":"2015"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408524.pdf?arnumber=11408524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:35:34Z","timestamp":1772692534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408524","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}