{"id":"https://openalex.org/W4362508600","doi":"https://doi.org/10.48550/arxiv.2303.17743","title":"FairGen: Towards Fair Graph Generation","display_name":"FairGen: Towards Fair Graph Generation","publication_year":2023,"publication_date":"2023-03-30","ids":{"openalex":"https://openalex.org/W4362508600","doi":"https://doi.org/10.48550/arxiv.2303.17743"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2303.17743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.17743","pdf_url":"https://arxiv.org/pdf/2303.17743","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/2303.17743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018530326","display_name":"Lecheng Zheng","orcid":"https://orcid.org/0000-0002-6869-3320"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng, Lecheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022696348","display_name":"Dawei Zhou","orcid":"https://orcid.org/0000-0002-7065-2990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dawei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068043486","display_name":"Hanghang Tong","orcid":"https://orcid.org/0000-0003-4405-3887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Hanghang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102267796","display_name":"Jiejun Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jiejun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101792548","display_name":"Yada Zhu","orcid":"https://orcid.org/0000-0002-3338-6371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yada","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073158087","display_name":"Jingrui He","orcid":"https://orcid.org/0000-0002-6429-6272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jingrui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018530326"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9861000180244446,"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":0.9861000180244446,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9110999703407288,"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/T13051","display_name":"Qualitative Comparative Analysis Research","score":0.9020000100135803,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7258939743041992},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6707466840744019},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6535118222236633},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5632399916648865},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.549310564994812},{"id":"https://openalex.org/keywords/social-graph","display_name":"Social graph","score":0.4368087947368622},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4198017120361328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3920915424823761},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1944696605205536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258939743041992},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6707466840744019},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6535118222236633},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5632399916648865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.549310564994812},{"id":"https://openalex.org/C2777522414","wikidata":"https://www.wikidata.org/wiki/Q648457","display_name":"Social graph","level":3,"score":0.4368087947368622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4198017120361328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3920915424823761},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1944696605205536},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2303.17743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.17743","pdf_url":"https://arxiv.org/pdf/2303.17743","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.2303.17743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.17743","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:2303.17743","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.17743","pdf_url":"https://arxiv.org/pdf/2303.17743","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362508600.pdf","grobid_xml":"https://content.openalex.org/works/W4362508600.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"tremendous":[3],"efforts":[4],"over":[5],"the":[6,11,37,40,56,65,70,74,82,117,123,131,160,163,169,173,198,237,242,249],"past":[7],"decades":[8],"dedicated":[9],"to":[10,25,32,54,81,96,100,172,192,254],"generation":[12,99,149],"of":[13,19,43,119,125,162,195,201],"realistic":[14],"graphs":[15],"in":[16,48,64,69,122,241,256],"a":[17,135,146,152,180,205],"variety":[18],"domains,":[20],"ranging":[21],"from":[22,28,87,116,168],"social":[23],"networks":[24,31],"computer":[26],"networks,":[27],"gene":[29],"regulatory":[30],"online":[33],"transaction":[34],"networks.":[35],"Despite":[36],"remarkable":[38],"success,":[39],"vast":[41],"majority":[42],"these":[44],"works":[45],"are":[46,51],"unsupervised":[47],"nature":[49],"and":[50,84,108,151,165,245],"typically":[52],"trained":[53],"minimize":[55],"expected":[57],"graph":[58,98,126,137,148,186,228],"reconstruction":[59],"loss,":[60],"which":[61,189],"would":[62],"result":[63],"representation":[66,120,154,238],"disparity":[67,121,239],"issue":[68],"generated":[71,243],"graphs,":[72,217,244],"i.e.,":[73],"protected":[75,164],"groups":[76],"(often":[77],"minorities)":[78],"contribute":[79],"less":[80],"objective":[83],"thus":[85],"suffer":[86],"systematically":[88],"higher":[89],"errors.":[90],"In":[91,112,176],"this":[92],"paper,":[93],"we":[94,114,133,178],"aim":[95],"tailor":[97],"downstream":[101,257],"mining":[102],"tasks":[103,258],"by":[104,157,252],"leveraging":[105],"label":[106],"information":[107,200],"user-preferred":[109],"parity":[110],"constraints.":[111],"particular,":[113],"start":[115],"investigation":[118],"context":[124,182],"generative":[127,138,187,229],"models.":[128],"To":[129],"mitigate":[130],"disparity,":[132],"propose":[134,179],"fairness-aware":[136],"model":[139,143,250],"named":[140],"FairGen.":[141],"Our":[142],"jointly":[144],"trains":[145],"label-informed":[147],"module":[150,156],"fair":[153],"learning":[155,159],"progressively":[158],"behaviors":[161],"unprotected":[166],"groups,":[167],"`easy'":[170],"concepts":[171],"`hard'":[174],"ones.":[175],"addition,":[177],"generic":[181],"sampling":[183],"strategy":[184],"for":[185],"models,":[188],"is":[190],"proven":[191],"be":[193],"capable":[194],"fairly":[196],"capturing":[197],"contextual":[199],"each":[202],"group":[203],"with":[204,226],"high":[206],"probability.":[207],"Experimental":[208],"results":[209],"on":[210,224],"seven":[211],"real-world":[212],"data":[213,260],"sets,":[214],"including":[215],"web-based":[216],"demonstrate":[218],"that":[219],"FairGen":[220],"(1)":[221],"obtains":[222],"performance":[223,251],"par":[225],"state-of-the-art":[227],"models":[230],"across":[231],"nine":[232],"network":[233],"properties,":[234],"(2)":[235],"mitigates":[236],"issues":[240],"(3)":[246],"substantially":[247],"boosts":[248],"up":[253],"17%":[255],"via":[259],"augmentation.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}