{"id":"https://openalex.org/W4281861579","doi":"https://doi.org/10.1145/3534678.3539404","title":"Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage","display_name":"Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4281861579","doi":"https://doi.org/10.1145/3534678.3539404"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539404","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.03426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100445079","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6908-508X"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060669482","display_name":"Yuying Zhao","orcid":"https://orcid.org/0000-0003-1302-6544"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuying Zhao","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047581320","display_name":"Yushun Dong","orcid":"https://orcid.org/0000-0001-7504-6159"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yushun Dong","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004341287","display_name":"Huiyuan Chen","orcid":"https://orcid.org/0000-0002-6360-558X"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyuan Chen","raw_affiliation_strings":["Case Western Reserve University, Cleveland, OH, USA"],"affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, OH, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029588473","display_name":"Jundong Li","orcid":"https://orcid.org/0000-0002-1878-817X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jundong Li","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036086705","display_name":"Tyler Derr","orcid":"https://orcid.org/0000-0002-0080-5998"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Derr","raw_affiliation_strings":["Vanderbilt University, Nashville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100445079"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":7.7689,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.97661871,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1938","last_page":"1948"},"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":0.9962999820709229,"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":0.9962999820709229,"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":0.9958000183105469,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9908000230789185,"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/computer-science","display_name":"Computer science","score":0.7646284103393555},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6076483726501465},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5799327492713928},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.49680688977241516},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4936279058456421},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4899958670139313},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4892999827861786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4585748314857483},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4529711604118347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45046988129615784},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4441046714782715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4289632737636566},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.412321001291275},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3538297414779663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10603374242782593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646284103393555},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6076483726501465},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5799327492713928},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.49680688977241516},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4936279058456421},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4899958670139313},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4892999827861786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4585748314857483},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4529711604118347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45046988129615784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4441046714782715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4289632737636566},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.412321001291275},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3538297414779663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10603374242782593},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539404","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.03426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.03426","pdf_url":"https://arxiv.org/pdf/2206.03426","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.03426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.03426","pdf_url":"https://arxiv.org/pdf/2206.03426","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2040825624","https://openalex.org/W2130354913","https://openalex.org/W2547875792","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2914721378","https://openalex.org/W2945903605","https://openalex.org/W2954996726","https://openalex.org/W2962711740","https://openalex.org/W2963757395","https://openalex.org/W2964015378","https://openalex.org/W3034492151","https://openalex.org/W3035447285","https://openalex.org/W3036974265","https://openalex.org/W3042770487","https://openalex.org/W3048692209","https://openalex.org/W3099375322","https://openalex.org/W3103409210","https://openalex.org/W3117178429","https://openalex.org/W3133596390","https://openalex.org/W3156833186","https://openalex.org/W3169740828","https://openalex.org/W3171764584","https://openalex.org/W3177385106","https://openalex.org/W3181414820","https://openalex.org/W3192448376","https://openalex.org/W3206450082","https://openalex.org/W3208162967","https://openalex.org/W3210856765","https://openalex.org/W4205342726","https://openalex.org/W4206445139","https://openalex.org/W4212774754","https://openalex.org/W4213263686","https://openalex.org/W4283076536","https://openalex.org/W4283661164","https://openalex.org/W4287323365","https://openalex.org/W4289389616","https://openalex.org/W4290943352","https://openalex.org/W4294558607","https://openalex.org/W4295312788","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W3081694532","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W1969211203","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W1517958729","https://openalex.org/W2561132942","https://openalex.org/W2092272653"],"abstract_inverted_index":{"Graph":[0,133],"Neural":[1,134],"Networks":[2],"(GNNs)":[3],"have":[4],"shown":[5],"great":[6],"power":[7],"in":[8,27,61,98,122],"learning":[9,43],"node":[10],"representations":[11],"on":[12,174],"graphs.":[13],"However,":[14,63],"they":[15],"may":[16],"inherit":[17],"historical":[18],"prejudices":[19],"from":[20,45],"training":[21],"data,":[22],"leading":[23],"to":[24,79,108,111,137,168],"discriminatory":[25],"bias":[26],"predictions.":[28,99],"Although":[29],"some":[30],"work":[31],"has":[32],"developed":[33],"fair":[34,41,139,159],"GNNs,":[35],"most":[36],"of":[37,53,74,90,115,141,165],"them":[38],"directly":[39],"borrow":[40],"representation":[42],"techniques":[44],"non-graph":[46],"domains":[47],"without":[48],"considering":[49,116,150],"the":[50,72,80,113,157,166],"potential":[51],"problem":[52],"sensitive":[54,81,91],"attribute":[55],"leakage":[56,89],"caused":[57],"by":[58,126,143],"feature":[59,68,104,109,117,154],"propagation":[60,69,118],"GNNs.":[62],"we":[64,101,129,161],"empirically":[65],"observe":[66],"that":[67,178],"could":[70,94],"vary":[71],"correlation":[73,120,151],"previously":[75],"innocuous":[76],"non-sensitive":[77],"features":[78,142,149],"ones.":[82],"This":[83],"can":[84],"be":[85],"viewed":[86],"as":[87],"a":[88,181],"information":[92],"which":[93],"further":[95],"exacerbate":[96],"discrimination":[97],"Thus,":[100],"design":[102],"two":[103],"masking":[105,147],"strategies":[106],"according":[107],"correlations":[110],"highlight":[112],"importance":[114],"and":[119,146,187],"variation":[121,152],"alleviating":[123],"discrimination.":[124],"Motivated":[125],"our":[127],"analysis,":[128],"propose":[130],"Fair":[131],"View":[132],"Network":[135],"(FairVGNN)":[136],"generate":[138],"views":[140],"automatically":[144],"identifying":[145],"sensitive-correlated":[148],"after":[153],"propagation.":[155],"Given":[156],"learned":[158],"views,":[160],"adaptively":[162],"clamp":[163],"weights":[164],"encoder":[167],"avoid":[169],"using":[170],"sensitive-related":[171],"features.":[172],"Experiments":[173],"real-world":[175],"datasets":[176],"demonstrate":[177],"FairVGNN":[179],"enjoys":[180],"better":[182],"trade-off":[183],"between":[184],"model":[185],"utility":[186],"fairness.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-06-13T00:00:00"}