{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T07:05:30Z","timestamp":1767855930586,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673152","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"117-126","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Sparsity-Aware Communication for Distributed Graph Neural Network Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8438-0356","authenticated-orcid":false,"given":"Ujjaini","family":"Mukhopadhyay","sequence":"first","affiliation":[{"name":"University of California, Berkeley, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6755-3895","authenticated-orcid":false,"given":"Alok","family":"Tripathy","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, United States of America and Lawrence Berkeley National Lab, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0203-0372","authenticated-orcid":false,"given":"Oguz","family":"Selvitopi","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0957-701X","authenticated-orcid":false,"given":"Katherine","family":"Yelick","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, United States of America and Lawrence Berkeley National Lab, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-9038","authenticated-orcid":false,"given":"Aydin","family":"Buluc","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Lab, USA and University of California, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2016.10.001"},{"key":"e_1_3_2_1_3_1","volume-title":"Article 13","author":"Akbudak Kadir","year":"2018","unstructured":"Kadir Akbudak, Oguz Selvitopi, and Cevdet Aykanat. 2018. Partitioning Models for Scaling Parallel Sparse Matrix-Matrix Multiplication. TOPC 4, 3, Article 13 (2018), 34\u00a0pages."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M104253X"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1313"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Gray Ballard Ayd\u0131n Bulu\u00e7 James Demmel Laura Grigori Benjamin Lipshitz Oded Schwartz and Sivan Toledo. 2013. Communication optimal parallel multiplication of sparse random matrices. (2013) 222\u2013231.","DOI":"10.1145\/2486159.2486196"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2755573.2755613"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49487-6_4"},{"key":"e_1_3_2_1_9_1","unstructured":"\u00dcmit\u00a0V \u00c7ataly\u00fcrek Karen\u00a0D Devine Marcelo\u00a0Fonseca Faraj Lars Gottesb\u00fcren Tobias Heuer Henning Meyerhenke Peter Sanders Sebastian Schlag Christian Schulz Daniel Seemaier [n.d.]. More recent advances in (hyper) graph partitioning. Comput. Surveys ([n. d.])."},{"key":"e_1_3_2_1_10_1","volume-title":"Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:1801.10247","author":"Chen Jie","year":"2018","unstructured":"Jie Chen, Tengfei Ma, and Cao Xiao. 2018. Fastgcn: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:1801.10247 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"NCCL: Optimized primitives for collective multi-GPU communication. https:\/\/github.com\/NVIDIA\/nccl.","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. 2023. NCCL: Optimized primitives for collective multi-GPU communication. https:\/\/github.com\/NVIDIA\/nccl."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.12.002"},{"key":"e_1_3_2_1_13_1","first-page":"I","article-title":"Inductive Representation Learning on Large Graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30, I.\u00a0Guyon, U.\u00a0V. Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.). Curran Associates, Inc., 1024\u20131034. http:\/\/papers.nips.cc\/paper\/6703-inductive-representation-learning-on-large-graphs.pdf","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs. arXiv preprint arXiv:2005.00687","author":"Hu Weihua","year":"2020","unstructured":"Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open Graph Benchmark: Datasets for Machine Learning on Graphs. arXiv preprint arXiv:2005.00687 (2020)."},{"key":"e_1_3_2_1_15_1","first-page":"187","article-title":"Improving the accuracy, scalability, and performance of graph neural networks with ROC","volume":"2","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 2 (2020), 187\u2013198.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"G. Karypis and V. Kumar. 1998. A fast and high quality multilevel scheme for partitioning irregular graphs. 20 1 (1998) 359\u2013392.","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR).","author":"N.","unstructured":"Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.117"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480856"},{"key":"e_1_3_2_1_20_1","unstructured":"Nikolai Merkel Daniel Stoll Ruben Mayer and Hans-Arno Jacobsen. 2023. An Experimental Comparison of Partitioning Strategies for Distributed Graph Neural Network Training. arxiv:2308.15602\u00a0[cs.DC]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3461472"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2014.7004265"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA580199"},{"key":"e_1_3_2_1_24_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Thorpe John","year":"2021","unstructured":"John Thorpe, Yifan Qiao, Jonathan Eyolfson, Shen Teng, Guanzhou Hu, Zhihao Jia, Jinliang Wei, Keval Vora, Ravi Netravali, Miryung Kim, and Guoqing\u00a0Harry Xu. 2021. Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, 495\u2013514. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/thorpe"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433794"},{"key":"e_1_3_2_1_26_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_27_1","first-page":"673","article-title":"BNS-GCN: Efficient Full-graph Training of Graph Convolutional Networks with Partition-parallelism and Random Boundary Node Sampling","volume":"4","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Ang Li, Nam\u00a0Sung Kim, and Yingyan Lin. 2022. BNS-GCN: Efficient Full-graph Training of Graph Convolutional Networks with Partition-parallelism and Random Boundary Node Sampling. Proceedings of Machine Learning and Systems 4 (2022), 673\u2013693.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Zeng Hanqing","year":"2020","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. 2020. GraphSAINT: Graph Sampling based inductive learning method. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673152","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:28:44Z","timestamp":1758648524000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":30,"alternative-id":["10.1145\/3673038.3673152","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673152","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}