{"id":"https://openalex.org/W4404396610","doi":"https://doi.org/10.48550/arxiv.2411.04371","title":"ComFairGNN: Community Fair Graph Neural Network","display_name":"ComFairGNN: Community Fair Graph Neural Network","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4404396610","doi":"https://doi.org/10.48550/arxiv.2411.04371"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.04371","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04371","pdf_url":"https://arxiv.org/pdf/2411.04371","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.04371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058026954","display_name":"Yonas Sium","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sium, Yonas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100350165","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-8776-8730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9164000153541565,"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":0.5233989357948303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4975006878376007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4949595332145691},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.33218029141426086},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3246806561946869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30280768871307373},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20568498969078064}],"concepts":[{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5233989357948303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4975006878376007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4949595332145691},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.33218029141426086},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3246806561946869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30280768871307373},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20568498969078064}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.04371","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04371","pdf_url":"https://arxiv.org/pdf/2411.04371","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.04371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.04371","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.04371","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.04371","pdf_url":"https://arxiv.org/pdf/2411.04371","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8251360198","display_name":"CAREER:  Achieving Quality Information Extraction from Scientific Documents with Heterogeneous Weak Supervisions","funder_award_id":"2237831","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8731646854","display_name":"Dependable Data Driven Discovery","funder_award_id":"2152117","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404396610.pdf","grobid_xml":"https://content.openalex.org/works/W4404396610.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2111375262","https://openalex.org/W2317728013","https://openalex.org/W1991205173","https://openalex.org/W2391251536","https://openalex.org/W2109048960","https://openalex.org/W2741481635","https://openalex.org/W2362198218","https://openalex.org/W2338537463","https://openalex.org/W2183644707"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4],"become":[5],"the":[6,62,68,72,88],"leading":[7],"approach":[8,133],"for":[9,77],"addressing":[10],"graph":[11,73],"analytical":[12],"problems":[13],"in":[14,95,109,130,163],"various":[15],"real-world":[16],"scenarios.":[17],"However,":[18],"GNNs":[19,47,110,150],"may":[20],"produce":[21],"biased":[22],"predictions":[23],"against":[24],"certain":[25],"demographic":[26],"subgroups":[27],"due":[28,66],"to":[29,67,106,126],"node":[30],"attributes":[31],"and":[32,111,166],"neighbors":[33],"surrounding":[34],"a":[35,56,103,122,135],"node.":[36],"Most":[37],"current":[38,91],"research":[39],"on":[40,45,155],"GNN":[41,80,92],"fairness":[42,50,167],"focuses":[43],"predominantly":[44],"debiasing":[46,81,93,113,138],"using":[48],"oversimplified":[49],"evaluation":[51,64],"metrics,":[52],"which":[53],"can":[54],"give":[55],"misleading":[57],"impression":[58],"of":[59,71,90,97],"fairness.":[60],"Understanding":[61],"potential":[63],"paradoxes":[65],"complicated":[69],"nature":[70],"structure":[74],"is":[75],"crucial":[76],"developing":[78],"effective":[79],"mechanisms.":[82],"In":[83],"this":[84,116],"paper,":[85],"we":[86,101],"examine":[87],"effectiveness":[89,162],"methods":[94,114],"terms":[96],"unfairness":[98],"evaluation.":[99],"Specifically,":[100],"introduce":[102,120],"community-level":[104,128],"strategy":[105],"measure":[107],"bias":[108,129,142],"evaluate":[112],"at":[115],"level.":[117],"Further,":[118],"We":[119],"ComFairGNN,":[121],"novel":[123],"framework":[124],"designed":[125],"mitigate":[127],"GNNs.":[131],"Our":[132],"employs":[134],"learnable":[136],"coreset-based":[137],"function":[139],"that":[140],"addresses":[141],"arising":[143],"from":[144],"diverse":[145],"local":[146],"neighborhood":[147,151],"distributions":[148],"during":[149],"aggregation.":[152],"Comprehensive":[153],"evaluations":[154],"three":[156],"benchmark":[157],"datasets":[158],"demonstrate":[159],"our":[160],"model's":[161],"both":[164],"accuracy":[165],"metrics.":[168]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}