{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:49:15Z","timestamp":1782895755613,"version":"3.54.5"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,25]]},"DOI":"10.1109\/ipdps65963.2026.00068","type":"proceedings-article","created":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:55:16Z","timestamp":1782852916000},"page":"746-759","source":"Crossref","is-referenced-by-count":0,"title":["MeCache: Communication-Efficient Multi-GPU Heterogeneous Graph Neural Network Training"],"prefix":"10.1109","author":[{"given":"Gongqingjian","family":"Jiang","sequence":"first","affiliation":[{"name":"National University of Defense Technology,National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghan","family":"Jia","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiquan","family":"Lai","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3703356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269281"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330673"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467138"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2023.102335"},{"key":"ref9","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Adaptive sampling towards fast graph representation learning","volume":"31","author":"Huang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Fastgcn: fast learning with graph convolutional networks via importance sampling","author":"Chen","year":"2018"},{"key":"ref12","article-title":"Ogb-lsc: A large-scale challenge for machine learning on graphs","author":"Hu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00036"},{"key":"ref18","first-page":"845","article-title":"MicroRec: Efficient recommendation inference by hardware and data structure solutions","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Jiang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3305077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519554"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613142"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00071"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.14778\/3746405.3746408"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref27","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref28","volume-title":"graphlearn for pytorch","year":"2025"},{"key":"ref29","first-page":"165","article-title":"Legion: Automatically pushing the envelope of multi-gpu system for billion-scale gnn training","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Sun"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3589311"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0098-3004(93)90090-R"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980942"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14778\/3425879.3425883"},{"key":"ref36","article-title":"PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses","author":"Min","year":"2021"},{"key":"ref37","volume-title":"CUDA by Example: An Introduction to General-Purpose GPU Programming.","author":"Sanders","year":"2010"},{"key":"ref38","volume-title":"nccl","year":"2025"},{"key":"ref39","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"ref40","first-page":"22118","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/qss_a_00021"},{"key":"ref42","article-title":"Relational graph attention networks","author":"Busbridge","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.992"},{"key":"ref44","article-title":"Compressing large language models with pca without performance loss","author":"Bengtsson","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00198"},{"key":"ref46","first-page":"203","article-title":"Adaptive message quantization and parallelization for distributed full-graph gnn training","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Wan"},{"key":"ref47","article-title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","author":"Tailor","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3681968"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00020"},{"key":"ref50","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"}],"event":{"name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","location":"New Orleans, LA, USA","start":{"date-parts":[[2026,5,25]]},"end":{"date-parts":[[2026,5,29]]}},"container-title":["2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11575315\/11575316\/11575330.pdf?arnumber=11575330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:33:54Z","timestamp":1782894834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11575330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ipdps65963.2026.00068","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]}}}