{"id":"https://openalex.org/W4416017917","doi":"https://doi.org/10.1145/3746252.3761329","title":"FedGC: Contrastive-enhanced Subgraph Federated Learning with Grouping Pseudo-Label","display_name":"FedGC: Contrastive-enhanced Subgraph Federated Learning with Grouping Pseudo-Label","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017917","doi":"https://doi.org/10.1145/3746252.3761329"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091725820","display_name":"Kai Xi","orcid":"https://orcid.org/0009-0008-5251-2274"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Keao Xi","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078742009","display_name":"Nannan Wu","orcid":"https://orcid.org/0000-0001-9074-0827"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Wu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104075573","display_name":"Yiming Zhao","orcid":"https://orcid.org/0000-0002-6879-7509"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Zhao","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393027","display_name":"Wenjun Wang","orcid":"https://orcid.org/0000-0002-3325-7481"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wang","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091725820"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18351529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3468","last_page":"3477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8632000088691711,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.8632000088691711,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.043800000101327896,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.03739999979734421,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.508899986743927},{"id":"https://openalex.org/keywords/subgraph-isomorphism-problem","display_name":"Subgraph isomorphism problem","score":0.5013999938964844},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4408000111579895},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.35740000009536743},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.35600000619888306},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3555999994277954},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.313400000333786},{"id":"https://openalex.org/keywords/blossom-algorithm","display_name":"Blossom algorithm","score":0.2948000133037567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893999814987183},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C131992880","wikidata":"https://www.wikidata.org/wiki/Q2528185","display_name":"Subgraph isomorphism problem","level":3,"score":0.5013999938964844},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C61455927","wikidata":"https://www.wikidata.org/wiki/Q1030529","display_name":"Blossom algorithm","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C191241153","wikidata":"https://www.wikidata.org/wiki/Q6027240","display_name":"Induced subgraph isomorphism problem","level":5,"score":0.29440000653266907},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1998029376","https://openalex.org/W2023655578","https://openalex.org/W2131681506","https://openalex.org/W2962788915","https://openalex.org/W3090369187","https://openalex.org/W3168213397","https://openalex.org/W3182158470","https://openalex.org/W3209882608","https://openalex.org/W4281753687","https://openalex.org/W4290877458","https://openalex.org/W4310642160","https://openalex.org/W4318822841","https://openalex.org/W4382318655","https://openalex.org/W4385764191","https://openalex.org/W4389315073","https://openalex.org/W4394717695","https://openalex.org/W4403155240","https://openalex.org/W4412825877"],"related_works":[],"abstract_inverted_index":{"Graph":[0,44],"structures":[1],"are":[2],"widely":[3],"used":[4],"to":[5,55,91,146,172,193,223],"model":[6],"relational":[7],"data.":[8],"In":[9],"many":[10],"real-world":[11,207],"applications,":[12],"each":[13,191],"data":[14,30,36,58,86],"client":[15,126,169,175,192],"usually":[16],"holds":[17],"only":[18],"a":[19,117,135],"partial":[20],"subgraph":[21,49,57,106,119],"of":[22,42,102,157,198,220],"the":[23,40,79,92,139,155,167,180,196,217],"original":[24],"graph,":[25],"and":[26,149,186,200,213],"privacy":[27],"concerns":[28],"limit":[29],"exchange":[31],"between":[32,72,182],"clients.":[33],"This":[34],"decentralized":[35],"distribution":[37],"often":[38],"degrades":[39],"effectiveness":[41],"conventional":[43],"Neural":[45],"Networks":[46],"(GNNs).":[47],"Recently,":[48],"federated":[50,107,120],"learning":[51,108,170],"has":[52],"been":[53],"proposed":[54],"enable":[56],"collaborative":[59],"training":[60],"without":[61],"compromising":[62],"privacy.":[63],"However,":[64],"two":[65],"critical":[66],"challenges":[67],"remain:":[68],"(1)":[69],"Missing":[70],"links":[71],"subgraphs":[73,89],"from":[74],"different":[75],"clients":[76,104],"significantly":[77],"prevent":[78],"message-passing":[80],"process":[81,171],"in":[82,105],"GNNs.":[83],"(2)":[84],"Varying":[85],"distributions":[87,145],"across":[88],"lead":[90],"non-IID":[93],"issue":[94],"(e.g.,":[95],"node":[96],"label":[97,144],"skews),":[98],"which":[99],"require":[100],"personalization":[101],"local":[103,168,183,199],"scenarios.":[109],"To":[110],"address":[111],"these":[112,158],"challenges,":[113],"we":[114],"propose":[115],"FedGC,":[116],"novel":[118],"method":[121],"that":[122,209],"combines":[123],"pseudo":[124,143],"label-based":[125],"grouping":[127],"with":[128],"Local-Global":[129,163],"Contrastive":[130,164],"Tasks.":[131],"Specifically,":[132],"FedGC":[133,161,189,221],"initializes":[134],"random":[136],"graph":[137],"on":[138,154,205],"server,":[140],"leverages":[141],"predicted":[142],"group":[147],"clients,":[148],"assigns":[150],"aggregation":[151],"weights":[152],"based":[153],"similarity":[156],"distributions.":[159],"Additionally,":[160],"incorporates":[162],"tasks":[165],"into":[166],"achieve":[173],"personalized":[174],"parameter":[176],"update.":[177],"By":[178],"adjusting":[179],"balance":[181,197],"supervision":[184],"task":[185],"contrastive":[187],"task,":[188],"enables":[190],"effectively":[194],"control":[195],"global":[201],"information.":[202],"Extensive":[203],"experiments":[204],"six":[206],"datasets":[208],"cover":[210],"citation":[211],"networks":[212,215],"social":[214],"validate":[216],"superior":[218],"performance":[219],"compared":[222],"state-of-the-art":[224],"baselines.":[225]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}