{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:50:28Z","timestamp":1773154228344,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF","award":["CCF-1908843 and CNS-2006604"],"award-info":[{"award-number":["CCF-1908843 and CNS-2006604"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605584","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"264-273","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Group-based Hierarchical Federated Learning: Convergence, Group Formation, and Sampling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6778-8546","authenticated-orcid":false,"given":"Jiyao","family":"Liu","sequence":"first","affiliation":[{"name":"Computer and Information Sciences, Temple University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-2178","authenticated-orcid":false,"given":"Xinliang","family":"Wei","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, Temple University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2030-0283","authenticated-orcid":false,"given":"Xuanzhang","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, Temple University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0121-0953","authenticated-orcid":false,"given":"Hongchang","family":"Gao","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, Temple University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3511-0288","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer and Information Sciences, Temple University, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"e_1_3_2_1_2_1","first-page":"374","article-title":"Towards federated learning at scale: System design","volume":"1","author":"Bonawitz H.","year":"2019","unstructured":"[2] K.\u00a0Bonawitz, H.\u00a0Eichner, et\u00a0al., \u201cTowards federated learning at scale: System design,\u201d Proc. of MLSys, vol.\u00a01, pp. 374\u2013388, 2019.","journal-title":"Proc. of MLSys"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of AIStats","author":"McMahan E.","year":"2017","unstructured":"[3] B.\u00a0McMahan, E.\u00a0Moore, et\u00a0al., \u201cCommunication-efficient learning of deep networks from decentralized data,\u201d in Proc. of AIStats, 2017."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"e_1_3_2_1_5_1","volume-title":"Federated learning with non-IID data","author":"Zhao M.","year":"1806","unstructured":"[5] Y.\u00a0Zhao, M.\u00a0Li, L.\u00a0Lai, N.\u00a0Suda, D.\u00a0Civin, and V.\u00a0Chandra, \u201cFederated learning with non-IID data,\u201d arXiv preprint arXiv:1806.00582, 2018."},{"key":"e_1_3_2_1_6_1","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li A.","year":"2020","unstructured":"[6] T.\u00a0Li, A.\u00a0K. Sahu, et\u00a0al., \u201cFederated optimization in heterogeneous networks,\u201d Proc. of MLSys, vol.\u00a02, pp. 429\u2013450, 2020.","journal-title":"Proc. of MLSys"},{"key":"e_1_3_2_1_7_1","volume-title":"Proc. of ICML","author":"Karimireddy S.","year":"2020","unstructured":"[7] S.\u00a0P. Karimireddy, S.\u00a0Kale, et\u00a0al., \u201cScaffold: Stochastic controlled averaging for federated learning,\u201d in Proc. of ICML, 2020."},{"key":"e_1_3_2_1_8_1","volume-title":"Salvaging federated learning by local adaptation","author":"Yu E.","year":"2002","unstructured":"[8] T.\u00a0Yu, E.\u00a0Bagdasaryan, and V.\u00a0Shmatikov, \u201cSalvaging federated learning by local adaptation,\u201d arXiv preprint arXiv:2002.04758, 2020."},{"key":"e_1_3_2_1_9_1","volume-title":"Federated meta-learning with fast convergence and efficient communication","author":"Chen M.","year":"1802","unstructured":"[9] F.\u00a0Chen, M.\u00a0Luo, Z.\u00a0Dong, Z.\u00a0Li, and X.\u00a0He, \u201cFederated meta-learning with fast convergence and efficient communication,\u201d arXiv preprint arXiv:1802.07876, 2018."},{"key":"e_1_3_2_1_10_1","volume-title":"Robust federated learning in a heterogeneous environment","author":"Ghosh J.","year":"1906","unstructured":"[10] A.\u00a0Ghosh, J.\u00a0Hong, D.\u00a0Yin, and K.\u00a0Ramchandran, \u201cRobust federated learning in a heterogeneous environment,\u201d arXiv preprint arXiv:1906.06629, 2019."},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. of NeurIPS","author":"Luo F.","year":"2021","unstructured":"[11] M.\u00a0Luo, F.\u00a0Chen, et\u00a0al., \u201cNo fear of heterogeneity: Classifier calibration for federated learning with non-IID data,\u201d in Proc. of NeurIPS, 2021."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom53586.2022.9762352"},{"key":"e_1_3_2_1_13_1","first-page":"1","article-title":"Optimal user-edge assignment in hierarchical federated learning based on statistical properties and network topology constraints","volume":"9","author":"Mhaisen","year":"2021","unstructured":"[13] N.\u00a0Mhaisen, et\u00a0al., \u201cOptimal user-edge assignment in hierarchical federated learning based on statistical properties and network topology constraints,\u201d IEEE Trans. on Network Science and Engineering, vol.\u00a09, no.\u00a01, pp. 55\u201366, 2021.","journal-title":"IEEE Trans. on Network Science and Engineering"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00012"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. of NeurIPS","author":"Wang Q.","year":"2020","unstructured":"[15] J.\u00a0Wang, Q.\u00a0Liu, et\u00a0al., \u201cTackling the objective inconsistency problem in heterogeneous federated optimization,\u201d in Proc. of NeurIPS, 2020."},{"key":"e_1_3_2_1_16_1","volume-title":"\u201cDisentangled federated learning for tackling attributes skew via invariant aggregation and diversity transferring","author":"Luo","year":"2022","unstructured":"[16] Z.\u00a0Luo, et\u00a0al., \u201cDisentangled federated learning for tackling attributes skew via invariant aggregation and diversity transferring,\u201d preprint arXiv:2206.06818, 2022."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"e_1_3_2_1_18_1","volume-title":"Personalized federated learning: A meta-learning approach","author":"Fallah A.","year":"2002","unstructured":"[18] A.\u00a0Fallah, A.\u00a0Mokhtari, and A.\u00a0Ozdaglar, \u201cPersonalized federated learning: A meta-learning approach,\u201d arXiv preprint arXiv:2002.07948, 2020."},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. of NeurIPS","author":"Zhang S.","year":"2021","unstructured":"[19] J.\u00a0Zhang, S.\u00a0Guo, et\u00a0al., \u201cParameterized knowledge transfer for personalized federated learning,\u201d in Proc. of NeurIPS, 2021."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488756"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW51379.2020.00053"},{"key":"e_1_3_2_1_22_1","volume-title":"H-FL: A hierarchical communication-efficient and privacy-protected architecture for federated learning","author":"Yang","year":"2021","unstructured":"[22] H.\u00a0Yang, \u201cH-FL: A hierarchical communication-efficient and privacy-protected architecture for federated learning,\u201d arXiv preprint arXiv:2106.00275, 2021."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/NAS55553.2022.9925313"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796935"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3037554"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of ICML","author":"Hamer M.","year":"2020","unstructured":"[26] J.\u00a0Hamer, M.\u00a0Mohri, and A.\u00a0T. Suresh, \u201cFedBoost: A communication-efficient algorithm for federated learning,\u201d in Proc. of ICML, 2020."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16920"},{"key":"e_1_3_2_1_28_1","volume-title":"Cryptology ePrint Archive","author":"Nguyen P.","year":"2021","unstructured":"[28] T.\u00a0D. Nguyen, P.\u00a0Rieger, et\u00a0al., \u201cFlame: Taming backdoors in federated learning,\u201d Cryptology ePrint Archive, 2021."},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of ICLR","author":"Yang M.","year":"2021","unstructured":"[29] H.\u00a0Yang, M.\u00a0Fang, and J.\u00a0Liu, \u201cAchieving linear speedup with partial worker participation in non-IID federated learning,\u201d Proc. of ICLR, 2021."},{"key":"e_1_3_2_1_30_1","volume-title":"Client selection in nonconvex federated learning: Improved convergence analysis for optimal unbiased sampling strategy","author":"Wang Y.","year":"2022","unstructured":"[30] L.\u00a0Wang, Y.\u00a0Guo, T.\u00a0Lin, and X.\u00a0Tang, \u201cClient selection in nonconvex federated learning: Improved convergence analysis for optimal unbiased sampling strategy,\u201d arXiv preprint arXiv:2205.13925, 2022."},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. of ICLR","author":"Li K.","year":"2019","unstructured":"[31] X.\u00a0Li, K.\u00a0Huang, W.\u00a0Yang, S.\u00a0Wang, and Z.\u00a0Zhang, \u201cOn the convergence of FedAvg on non-IID data,\u201d in Proc. of ICLR, 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.05.034"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5103-0"},{"key":"e_1_3_2_1_34_1","volume-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"Warden","year":"1804","unstructured":"[34] P.\u00a0Warden, \u201cSpeech Commands: A Dataset for Limited-Vocabulary Speech Recognition,\u201d arXiv preprint arXiv:1804.03209, 2018."},{"key":"e_1_3_2_1_36_1","volume-title":"\u201cMeasuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"1909","unstructured":"[36] T.-M.\u00a0H. Hsu, et\u00a0al., \u201cMeasuring the effects of non-identical data distribution for federated visual classification,\u201d arXiv preprint arXiv:1909.06335, 2019."}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","location":"Salt Lake City UT USA","acronym":"ICPP 2023"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605584","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605584"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":35,"alternative-id":["10.1145\/3605573.3605584","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605584","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}