{"id":"https://openalex.org/W4405029781","doi":"https://doi.org/10.48550/arxiv.2411.18905","title":"FedRGL: Robust Federated Graph Learning for Label Noise","display_name":"FedRGL: Robust Federated Graph Learning for Label Noise","publication_year":2024,"publication_date":"2024-11-28","ids":{"openalex":"https://openalex.org/W4405029781","doi":"https://doi.org/10.48550/arxiv.2411.18905"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.18905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18905","pdf_url":"https://arxiv.org/pdf/2411.18905","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.18905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101859272","display_name":"De Li","orcid":"https://orcid.org/0000-0002-4360-4010"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, De","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056287349","display_name":"Haodong Qian","orcid":"https://orcid.org/0009-0006-3530-7530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102023186","display_name":"Qiyu Li","orcid":"https://orcid.org/0009-0002-7308-1334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031121873","display_name":"Tan Zhou","orcid":"https://orcid.org/0000-0002-0792-1676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gan, Zemin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Zemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008413512","display_name":"Jinyan Wang","orcid":"https://orcid.org/0000-0002-2462-1499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037037839","display_name":"Xianxian Li","orcid":"https://orcid.org/0000-0002-7083-3847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xianxian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8806999921798706,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14484","display_name":"Technology and Data Analysis","score":0.8655999898910522,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.828499972820282,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6618360280990601},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5367506742477417},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44358253479003906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3741772770881653},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.28301772475242615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6618360280990601},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5367506742477417},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44358253479003906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3741772770881653},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28301772475242615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.18905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18905","pdf_url":"https://arxiv.org/pdf/2411.18905","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.18905","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.18905","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.18905","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.18905","pdf_url":"https://arxiv.org/pdf/2411.18905","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405029781.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Federated":[0],"Graph":[1],"Learning":[2],"(FGL)":[3],"is":[4],"a":[5,60],"distributed":[6],"machine":[7],"learning":[8,40,64],"paradigm":[9],"based":[10],"on":[11,44,131],"graph":[12,22,63,96,134],"neural":[13],"networks,":[14],"enabling":[15,121],"secure":[16],"and":[17,83,103,148],"collaborative":[18],"modeling":[19],"of":[20,118,125,150],"local":[21],"data":[23],"among":[24],"clients.":[25,151],"However,":[26],"label":[27,38,67],"noise":[28,39,75,145],"can":[29],"degrade":[30],"the":[31,80,126],"global":[32,81,127],"model's":[33],"generalization":[34],"performance.":[35],"Existing":[36],"federated":[37,62],"methods,":[41],"primarily":[42],"focused":[43],"computer":[45],"vision,":[46],"often":[47],"yield":[48],"suboptimal":[49],"results":[50],"when":[51],"applied":[52],"to":[53,107],"FGL.":[54],"To":[55,90],"address":[56],"this,":[57],"we":[58,94,111],"propose":[59],"robust":[61,123],"method":[65],"with":[66],"noise,":[68],"termed":[69],"FedRGL.":[70],"FedRGL":[71,138],"introduces":[72],"dual-perspective":[73],"consistency":[74],"node":[76],"filtering,":[77],"leveraging":[78],"both":[79],"model":[82,113],"subgraph":[84],"structure":[85],"under":[86],"class-aware":[87],"dynamic":[88],"thresholds.":[89],"enhance":[91],"client-side":[92],"training,":[93],"incorporate":[95],"contrastive":[97],"learning,":[98],"which":[99],"improves":[100],"encoder":[101],"robustness":[102],"assigns":[104],"high-confidence":[105],"pseudo-labels":[106],"noisy":[108],"nodes.":[109],"Additionally,":[110],"measure":[112],"quality":[114],"via":[115],"predictive":[116],"entropy":[117],"unlabeled":[119],"nodes,":[120],"adaptive":[122],"aggregation":[124],"model.":[128],"Comparative":[129],"experiments":[130],"multiple":[132],"real-world":[133],"datasets":[135],"show":[136],"that":[137],"outperforms":[139],"12":[140],"baseline":[141],"methods":[142],"across":[143],"various":[144],"rates,":[146],"types,":[147],"numbers":[149]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}