{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:45Z","timestamp":1750309545192,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714741","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"786-795","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GraphCom: Communication Hierarchy-aware Graph Engine for Distributed Model Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3622-1772","authenticated-orcid":false,"given":"Xinbiao","family":"Gan","sequence":"first","affiliation":[{"name":"School of Computer, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9486-420X","authenticated-orcid":false,"given":"Tiejun","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1187-9026","authenticated-orcid":false,"given":"Liang","family":"Wu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5234-1937","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7892-2617","authenticated-orcid":false,"given":"Lingyun","family":"Song","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwest Polytechnical University, Chanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0058-2350","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9740-0056","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4907-306X","authenticated-orcid":false,"given":"Kai","family":"Lu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. https:\/\/en.wikipedia.org\/wiki\/Message_Passing_Interface. (2024)."},{"key":"e_1_3_2_1_2_1","unstructured":"2024. https:\/\/en.wikipedia.org\/wiki\/SPMD. (2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"2024. https:\/\/github.com\/graph500\/graph500\/tree\/newreference\/aml. (2024)."},{"key":"e_1_3_2_1_4_1","unstructured":"2024. https:\/\/graph500.org\/. (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"2024. https:\/\/top500.org\/. (2024)."},{"volume-title":"USENIX Annual Technical Conference (ATC 17)","author":"Ai Zhiyuan","key":"e_1_3_2_1_6_1","unstructured":"Zhiyuan Ai, Mingxing Zhang, Yongwei Wu, Xuehai Qian, and Weimin Zheng. [n.d.]. Squeezing out All the Value of Loaded Data: An Out-of-core Graph Processing System with Reduced Disk I\/O. In USENIX Annual Technical Conference (ATC 17). USENIX Association."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.22"},{"key":"e_1_3_2_1_8_1","volume-title":"European Conference on Computer Systems","author":"Chen R.","year":"2015","unstructured":"R. Chen, J. Shi, Y. Chen, and H. Chen. 2015. Powerlyra: Differentiated graph computation and partitioning on skewed graphs. European Conference on Computer Systems (2015), 1--15."},{"key":"e_1_3_2_1_9_1","first-page":"852","article-title":"Weaver: a high-performance, transactional graph database based on refinable timestamps","volume":"9","author":"Dubey Ayush","year":"2016","unstructured":"Ayush Dubey, Greg D Hill, Robert Escriva, and Emin G\u00fcn Sirer. 2016. Weaver: a high-performance, transactional graph database based on refinable timestamps. PVLDB 9, 11 (2016), 852--863.","journal-title":"PVLDB"},{"key":"e_1_3_2_1_10_1","first-page":"156","article-title":"The graph Voronoi diagram with applications. Networks","volume":"36","author":"Erwig Martin","year":"2000","unstructured":"Martin Erwig. 2000. The graph Voronoi diagram with applications. Networks: An International Journal 36, 3 (2000), 156--163.","journal-title":"An International Journal"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476369"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035942"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2009.12"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3676846"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638498"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3100785"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00199"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 10th USENIX conference on Operating Systems Design and Implementation. 17--30","author":"Gonzalez Joseph E.","year":"2012","unstructured":"Joseph E. Gonzalez, Yucheng Low, Haijie Gu, Danny Bickson, and Carlos Guestrin. 2012. PowerGraph: distributed graph-parallel computation on natural graphs. In Proceedings of the 10th USENIX conference on Operating Systems Design and Implementation. 17--30."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 11th USENIX conference on Operating Systems Design and Implementation. 599--613","author":"Gonzalez Joseph E.","year":"2014","unstructured":"Joseph E. Gonzalez, Reynold S. Xin, Ankur Dave, Daniel Crankshaw, Michael J. Franklin, and Ion Stoica. 2014. GraphX: graph processing in a distributed dataflow framework. In Proceedings of the 11th USENIX conference on Operating Systems Design and Implementation. 599--613."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178506"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/2904483.2904486"},{"key":"e_1_3_2_1_22_1","volume-title":"Version Traveler: Fast and Memory-Efficient Version Switching in Graph Processing Systems. In 2016 USENIX Annual Technical Conference (USENIX ATC 16)","author":"Ju Xiaoen","year":"2016","unstructured":"Xiaoen Ju, Dan Williams, Hani Jamjoom, and Kang G Shin. 2016. Version Traveler: Fast and Memory-Efficient Version Switching in Graph Processing Systems. In 2016 USENIX Annual Technical Conference (USENIX ATC 16)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.73"},{"key":"e_1_3_2_1_24_1","volume-title":"Graphchi: Large-scale graph computation on just a pc. In Presented as part of the 10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12). 31--46.","author":"Kyrola Aapo","year":"2012","unstructured":"Aapo Kyrola, Guy Blelloch, and Carlos Guestrin. 2012. Graphchi: Large-scale graph computation on just a pc. In Presented as part of the 10th USENIX Symposium on Operating Systems Design and Implementation (OSDI 12). 31--46."},{"key":"e_1_3_2_1_25_1","volume-title":"Kronecker Graphs: An Approach to Modeling Networks. ArXiv abs\/0812.4905","author":"Leskovec J.","year":"2010","unstructured":"J. Leskovec, Deepayan Chakrabarti, J. Kleinberg, C. Faloutsos, and Zoubin Ghahramani. 2010. Kronecker Graphs: An Approach to Modeling Networks. ArXiv abs\/0812.4905 (2010)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3084451"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2014.6968755"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"volume-title":"USENIX Annual Technical Conference (ATC 17)","author":"Ma Lingxiao","key":"e_1_3_2_1_29_1","unstructured":"Lingxiao Ma, Han Chen, Jilong Xue, and Yafei Dai. [n.d.]. Garaph: Efficient GPU-accelerated Graph Processing on a Single Machine with Balanced Replication. In USENIX Annual Technical Conference (ATC 17). USENIX Association."},{"key":"e_1_3_2_1_30_1","volume-title":"Pregel: a system for large-scale graph processing. Sigmod","author":"Malewicz Grzegorz","year":"2009","unstructured":"Grzegorz Malewicz, Matthew H. Austern, Aart J. C. Bik, James C. Dehnert, Ilan Horn, Naty Leiser, and Grzegorz Czajkowski. 2009. Pregel: a system for large-scale graph processing. Sigmod (2009), 135--146."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2016.92"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213854"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2612182"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00053"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173180"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-017-0034-4"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1998.669923"},{"key":"e_1_3_2_1_39_1","volume-title":"Unifying Graph Neural Networks with a Generalized Optimization Framework. ACM Transactions on Information Systems","author":"Shi Chuan","year":"2024","unstructured":"Chuan Shi, Meiqi Zhu, Yue Yu, Xiao Wang, and Junping Du. 2024. Unifying Graph Neural Networks with a Generalized Optimization Framework. ACM Transactions on Information Systems (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026902"},{"key":"e_1_3_2_1_41_1","unstructured":"Naoyuki Shida S. Sumimoto and Atsuya Uno. 2012. MPI Library and Low-Level Communication on the K computer."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Hiroaki Shiokawa Yasuhiro Fujiwara and Makoto Onizuka. 2013. Fast algorithm for modularity-based graph clustering.. In AAAI. 1170--1176.","DOI":"10.1609\/aaai.v27i1.8455"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/2672596.2672664"},{"key":"e_1_3_2_1_46_1","volume-title":"ICLR workshop on representation learning on graphs and manifolds.","author":"Wang Minjie Yu","year":"2019","unstructured":"Minjie Yu Wang. 2019. Deep graph library: Towards efficient and scalable deep learning on graphs. In ICLR workshop on representation learning on graphs and manifolds."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2020.9010009"},{"key":"e_1_3_2_1_48_1","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Xiao Wencong","year":"2017","unstructured":"Wencong Xiao, Jilong Xue, Youshan Miao, Zhen Li, Cheng Chen, Ming Wu, Wei Li, and Lidong Zhou. 2017. Tux2: Distributed Graph Computation for Machine Learning. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, 669--682."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733085.2733097"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1561\/1900000056"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733085.2733103"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213895"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.63"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 2nd USENIX conference on Hot topics in cloud computing","volume":"10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: cluster computing with working sets. In Proceedings of the 2nd USENIX conference on Hot topics in cloud computing, Vol. 10. 10."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645682"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026900"},{"key":"e_1_3_2_1_57_1","volume-title":"GraphA: Efficient Partitioning and Storage for Distributed Graph Computation","author":"Zhang Yiming","year":"2017","unstructured":"Yiming Zhang, Dongsheng Li, Chengfei Zhang, Jinyan Wang, and Ling Liu. 2017. GraphA: Efficient Partitioning and Storage for Distributed Graph Computation. IEEE Transactions on Services Computing (2017)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3020813"},{"key":"e_1_3_2_1_59_1","volume-title":"Gemini: A Computation-Centric Distributed Graph Processing System. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016","author":"Zhu Xiaowei","year":"2016","unstructured":"Xiaowei Zhu, Wenguang Chen, Weimin Zheng, and Xiaosong Ma. 2016. Gemini: A Computation-Centric Distributed Graph Processing System. In 12th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2016, Savannah, GA, USA, November 2--4, 2016, Kimberly Keeton and Timothy Roscoe (Eds.). USENIX Association, 301--316. https:\/\/www.usenix.org\/conference\/osdi16\/ technical-sessions\/presentation\/zhu"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714741","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:41Z","timestamp":1750295921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":59,"alternative-id":["10.1145\/3696410.3714741","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714741","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}