{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:11:11Z","timestamp":1770354671583,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545082","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MG-GCN: A Scalable multi-GPU GCN Training Framework"],"prefix":"10.1145","author":[{"given":"Muhammed Fatih","family":"Balin","sequence":"first","affiliation":[{"name":"Computational Science and Engineering, Georgia Institute of Technology, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaan","family":"Sancak","sequence":"additional","affiliation":[{"name":"Computational Science and Engineering, Georgia Institute of Technology, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umit V.","family":"Catalyurek","sequence":"additional","affiliation":[{"name":"Computational Science and Engineering, Georgia Institute of Technology, United States of America and Amazon Web Services, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen 2015. TensorFlow Large-scale machine learning on heterogeneous systems."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1958598.1958611"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations.","author":"Chen Jie","year":"2018","unstructured":"Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_6_1","unstructured":"Tianqi Chen Mu Li Yutian Li Min Lin Naiyan Wang 2015. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. arxiv:1512.01274\u00a0[cs.DC]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1337\u20131345","author":"Coates Adam","year":"2013","unstructured":"Adam Coates, Brody Huval, Tao Wang, David Wu, Bryan Catanzaro, and Ng Andrew. 2013. Deep learning with COTS HPC systems. In International conference on machine learning. PMLR, 1337\u20131345."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1958.tb00292.x"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"e_1_3_2_1_11_1","volume-title":"On the performance of network parallel training in artificial neural networks. arXiv","author":"Ericson Ludvig","year":"2017","unstructured":"Ludvig Ericson and Rendani Mbuvha. 2017. On the performance of network parallel training in artificial neural networks. arXiv (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop.","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan\u00a0Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. In ICLR Workshop."},{"key":"e_1_3_2_1_13_1","volume-title":"PIGO: A Parallel Graph Input\/Output Library. In IEEE IPDP Workshops. 276\u2013279","author":"Kasimir","unstructured":"Kasimir Gabert and \u00dcmit\u00a0V. \u00c7ataly\u00fcrek. 2021. PIGO: A Parallel Graph Input\/Output Library. In IEEE IPDP Workshops. 276\u2013279."},{"key":"e_1_3_2_1_14_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Gandhi Swapnil","year":"2021","unstructured":"Swapnil Gandhi and Anand\u00a0P. Iyer. 2021. P3: Distributed Deep Graph Learning at Scale. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, 551\u2013568."},{"key":"e_1_3_2_1_15_1","unstructured":"Boris Ginsburg Igor Gitman and Yang You. 2018. Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling."},{"key":"e_1_3_2_1_16_1","unstructured":"Joseph\u00a0E Gonzalez Yucheng Low Haijie Gu Danny Bickson and Carlos Guestrin. 2012. PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In OSDI\u201912. 17\u201330."},{"key":"e_1_3_2_1_17_1","volume-title":"large minibatch sgd: Training imagenet in 1 hour. arXiv","author":"Goyal Priya","year":"2017","unstructured":"Priya Goyal, Piotr Doll\u00e1r, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, 2017. Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv (2017)."},{"key":"e_1_3_2_1_18_1","unstructured":"William\u00a0L. Hamilton Rex Ying and Jure Leskovec. 2018. Inductive Representation Learning on Large Graphs. arxiv:1706.02216\u00a0[cs.SI]"},{"key":"e_1_3_2_1_19_1","unstructured":"Weihua Hu Matthias Fey Marinka Zitnik Yuxiao Dong Hongyu Ren 2021. Open Graph Benchmark: Datasets for Machine Learning on Graphs. arxiv:2005.00687\u00a0[cs.LG]"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Jia Zhihao","year":"2020","unstructured":"Zhihao Jia, Sina Lin, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2020. Improving the accuracy, scalability, and performance of graph neural networks with roc. Proceedings of Machine Learning and Systems (MLSys) (2020), 187\u2013198."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_2_1_23_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2017","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv:1412.6980\u00a0[cs.LG]"},{"key":"e_1_3_2_1_24_1","volume-title":"Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations. OpenReview.net.","author":"N.","unstructured":"Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/130914218"},{"key":"e_1_3_2_1_26_1","volume-title":"One weird trick for parallelizing convolutional neural networks. arXiv","author":"Krizhevsky Alex","year":"2014","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. arXiv (2014)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_2_1_29_1","volume-title":"NeuGraph: Parallel Deep Neural Network Computation on Large Graphs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Ma Lingxiao","year":"2019","unstructured":"Lingxiao Ma, Zhi Yang, Youshan Miao, Jilong Xue, Ming Wu, 2019. NeuGraph: Parallel Deep Neural Network Computation on Large Graphs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19). USENIX Association, 443\u2013458."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"e_1_3_2_1_31_1","volume-title":"Rectified Linear Units Improve Restricted Boltzmann Machines. In International Conference on International Conference on Machine Learning. 807\u2013814","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey\u00a0E. Hinton. 2010. Rectified Linear Units Improve Restricted Boltzmann Machines. In International Conference on International Conference on Machine Learning. 807\u2013814."},{"key":"e_1_3_2_1_32_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS. 8024\u20138035."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433794"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"e_1_3_2_1_37_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. arxiv:1710.10903\u00a0[stat.ML]"},{"key":"e_1_3_2_1_38_1","volume-title":"Highly-Performant Package for Graph Neural Networks. arXiv","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, 2019. Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks. arXiv (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, 2021. GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, 515\u2013531."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems, Vol.\u00a027. Curran Associates","author":"Xie Cong","unstructured":"Cong Xie, Ling Yan, Wu-Jun Li, and Zhihua Zhang. 2014. Distributed Power-law Graph Computing: Theoretical and Empirical Analysis. In Advances in Neural Information Processing Systems, Vol.\u00a027. Curran Associates, Inc."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2319813"},{"key":"e_1_3_2_1_42_1","first-page":"5165","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang Muhan","year":"2018","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. NIPS 31(2018), 5165\u20135175.","journal-title":"NIPS"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"},{"key":"e_1_3_2_1_46_1","unstructured":"Martin Zinkevich Markus Weimer Alexander\u00a0J Smola and Lihong Li. 2010. Parallelized stochastic gradient descent.. In NIPS Vol.\u00a04."}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545082","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:44Z","timestamp":1750186964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":46,"alternative-id":["10.1145\/3545008.3545082","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545082","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}