{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T23:05:34Z","timestamp":1782947134530,"version":"3.54.5"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tmc.2025.3641696","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:35:23Z","timestamp":1765305323000},"page":"6929-6947","source":"Crossref","is-referenced-by-count":3,"title":["Toward Communication-Efficient Decentralized Federated Graph Learning Over Non-IID Data"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5438-6538","authenticated-orcid":false,"given":"Shilong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1764-9303","authenticated-orcid":false,"given":"Jianchun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7974-0160","authenticated-orcid":false,"given":"Chenxia","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8684-3495","authenticated-orcid":false,"given":"Qianpiao","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8417-3256","authenticated-orcid":false,"given":"Liusheng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123876"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/pcn.13804"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645517"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/97\/20241175"},{"key":"ref5","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"ref6","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3363089"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3424301"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2025.3539666"},{"key":"ref10","first-page":"18839","article-title":"Federated graph classification over non-iid graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie","year":"2021"},{"key":"ref11","first-page":"6671","article-title":"Subgraph federated learning with missing neighbor generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118354"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3315451"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3492140"},{"key":"ref15","article-title":"Decentralized federated graph neural networks","volume-title":"Proc. Int. Workshop Federated Transfer Learn. Data Sparsity Confidentiality Conjunction IJCAI","author":"Pei","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS52092.2021.9521331"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2022.3187149"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ton.2025.3600015"},{"key":"ref19","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2020.3026229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3376636"},{"key":"ref22","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3125565"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS54832.2022.9812908"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3654947"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3178378"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2883662"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"5686","DOI":"10.1142\/12037","article-title":"Consensus control for decentralized deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kong","year":"2021"},{"key":"ref30","article-title":"Decentralized deep learning with arbitrary communication compression","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Koloskova","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICC47138.2019.9123209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690665"},{"key":"ref34","article-title":"Fedgraphnn: A federated learning system and benchmark for graph neural networks","author":"He","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00040"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118424"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2934002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228945"},{"key":"ref39","first-page":"4387","article-title":"The non-iid data quagmire of decentralized machine learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hsieh","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/800070.802199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.02.022"},{"key":"ref45","article-title":"Nvidia jetson devices","year":"2024"},{"issue":"2","key":"ref46","article-title":"Docker: Lightweight linux containers for consistent development and deployment","volume":"239","author":"Merkel","year":"2014","journal-title":"Linux j"},{"key":"ref47","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref48","article-title":"socket library","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3369188"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3329005"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.23919\/ICN.2024.0008"},{"key":"ref52","article-title":"DFed-SST: Building semantic-and structure-aware topologies for decentralized federated graph learning","author":"Guo","year":"2025"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-024-00294-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3661821"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10721-6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3360429"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/426"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106148"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119976"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29468"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3240527"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679725"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3315746"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20643"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3340880"},{"key":"ref67","article-title":"Federated graph learning with adaptive importance-based sampling","author":"Li","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3159688"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref70","article-title":"Improving federated relational data modeling via basis alignment and weight penalty","author":"Lin","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30637-2_50"},{"key":"ref72","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"ref73","first-page":"305","article-title":"In search of an understandable consensus algorithm","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Ongaro","year":"2014"},{"key":"ref74","first-page":"5381","article-title":"A unified theory of decentralized sgd with changing topology and local updates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koloskova","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11471282\/11288048.pdf?arnumber=11288048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T03:57:21Z","timestamp":1775620641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11288048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":75,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3641696","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}