{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:55:07Z","timestamp":1772934907445,"version":"3.50.1"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402486","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"1222-1231","source":"Crossref","is-referenced-by-count":0,"title":["Staleness-Based Subgraph Sampling for Training GNNs on Large-Scale Graphs"],"prefix":"10.1109","author":[{"given":"Limei","family":"Wang","sequence":"first","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanqing","family":"Zeng","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Hua","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaveh","family":"Hassani","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Malevich","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Long","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuiwang","family":"Ji","sequence":"additional","affiliation":[{"name":"Texas A&M University,College Station,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref2","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kipf","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012757468803412"},{"key":"ref4","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Gasteiger","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume":"33","author":"Corso","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Chen","year":"2020"},{"key":"ref8","first-page":"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":"ref9","article-title":"OGBLSC: A large-scale challenge for machine learning on graphs","volume-title":"Thirtyfifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Hu","year":"2021"},{"key":"ref10","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"International conference on machine learning","author":"Gilmer","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1039\/C7SC02664A"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"ref14","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref16","article-title":"Refresh: Reducing memory access from exploiting stable historical embeddings for graph neural network training","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2018"},{"key":"ref18","article-title":"Adaptive sampling towards fast graph representation learning","volume":"31","author":"Huang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume":"32","author":"Zou","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1123"},{"key":"ref21","article-title":"GraphSAINT: Graph sampling based inductive learning method","author":"Zeng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","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":"ref23","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":"ref24","first-page":"25684","article-title":"Graphfm: Improving large-scale gnn training via feature momentum","volume-title":"International Conference on Machine Learning","author":"Yu","year":"2022"},{"key":"ref25","article-title":"LMC: Fast training of GNNs via subgraph sampling with provable convergence","volume-title":"The Eleventh International Conference on Learning Representations","author":"Shi","year":"2023"},{"key":"ref26","article-title":"Stochastic training of graph convolutional networks with variance reduction","author":"Chen","year":"2017","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403192"},{"key":"ref28","first-page":"9","article-title":"Influence-based minibatching for graph neural networks","volume-title":"Learning on Graphs Conference","author":"Gasteiger","year":"2022"},{"key":"ref29","article-title":"Gnnpipe: Accelerating distributed fullgraph gnn training with pipelined model parallelism","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.14778\/3538598.3538614"},{"key":"ref31","first-page":"673","article-title":"Bns-gcn: Efficient fullgraph training of graph convolutional networks with partition-parallelism and random boundary node sampling","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Wan","year":"2022"},{"key":"ref32","article-title":"Staleness-alleviated distributed gnn training via online dynamic-embedding prediction","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"International conference on machine learning","author":"Wu","year":"2019"},{"key":"ref34","article-title":"SIGN: Scalable inception graph neural networks","author":"Frasca","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Scalable graph neural networks for heterogeneous graphs","author":"Yu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Scalable and adaptive graph neural networks with self-label-enhanced training","author":"Sun","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539121"},{"key":"ref38","article-title":"Nagphormer: A tokenized graph transformer for node classification in large graphs","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen","year":"2022"},{"key":"ref39","article-title":"VCR-graphormer: A mini-batch graph transformer via virtual connections","volume-title":"The Twelfth International Conference on Learning Representations","author":"Fu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"ref41","article-title":"Combining label propagation and simple models out-performs graph neural networks","author":"Huang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Node feature extraction by self-supervised multi-scale neighborhood prediction","author":"Chien","year":"2021","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00016"},{"key":"ref44","article-title":"Scr: Training graph neural networks with consistency regularization","author":"Zhang","year":"2021","journal-title":"arXiv e-prints"},{"key":"ref45","article-title":"MLPInit: Embarrassingly simple GNN training acceleration with MLP initialization","volume-title":"The Eleventh International Conference on Learning Representations","author":"Han","year":"2023"},{"key":"ref46","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"International conference on machine learning","author":"Li","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0388"},{"key":"ref48","article-title":"Simplifying and empowering transformers for large-graph representations","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Wu","year":"2023"},{"key":"ref49","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1054"},{"key":"ref51","article-title":"Hyena hierarchy: Towards larger convolutional language models","author":"Poli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672044"},{"key":"ref53","article-title":"Graph-mamba: Towards long-range graph sequence modeling with selective state spaces","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","volume-title":"A fast and effective alternative to graph transformers","author":"Sancak","year":"2024"},{"key":"ref55","article-title":"Simplifying and empowering transformers for large-graph representations","volume":"36","author":"Wu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref56","first-page":"31613","article-title":"Exphormer: Sparse transformers for graphs","volume-title":"International Conference on Machine Learning","author":"Shirzad","year":"2023"},{"key":"ref57","first-page":"12724","article-title":"A generalization of vit\/mlp-mixer to graphs","volume-title":"International Conference on Machine Learning","author":"He","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34231"},{"key":"ref59","article-title":"Learning graph quantized tokenizers","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang","year":"2025"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/s1064827595287997"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1970.tb01770.x"},{"key":"ref63","volume-title":"Metis: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices","author":"Karypis","year":"1997"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1997.1404"},{"key":"ref65","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Fey","year":"2019"},{"key":"ref67","first-page":"1756","article-title":"Open problem: The landscape of the loss surfaces of multilayer networks","volume-title":"Conference on Learning Theory","author":"Choromanska","year":"2015"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402486.pdf?arnumber=11402486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:20:02Z","timestamp":1772868002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402486","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}