{"id":"https://openalex.org/W4401856733","doi":"https://doi.org/10.1145/3637528.3671741","title":"Balanced Confidence Calibration for Graph Neural Networks","display_name":"Balanced Confidence Calibration for Graph Neural Networks","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401856733","doi":"https://doi.org/10.1145/3637528.3671741"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671741","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671741","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671741","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102002749","display_name":"Hao Yang","orcid":"https://orcid.org/0000-0002-8013-9023"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["National University of Defense Technology, ChangSha, China"],"raw_orcid":"https://orcid.org/0000-0002-8013-9023","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757169","display_name":"Min Wang","orcid":"https://orcid.org/0000-0002-6306-2589"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Wang","raw_affiliation_strings":["National University of Defense Technology, ChangSha, China"],"raw_orcid":"https://orcid.org/0000-0002-6306-2589","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341185","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0001-6135-6965"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["National University of Defense Technology, ChangSha, China"],"raw_orcid":"https://orcid.org/0000-0001-6135-6965","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028043255","display_name":"Mingrui Lao","orcid":"https://orcid.org/0000-0001-8413-7220"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingrui Lao","raw_affiliation_strings":["National University of Defense Technology, ChangSha, China"],"raw_orcid":"https://orcid.org/0000-0001-8413-7220","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022422213","display_name":"Yun Zhou","orcid":"https://orcid.org/0000-0001-7328-0275"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhou","raw_affiliation_strings":["National University of Defense Technology, ChangSha, China"],"raw_orcid":"https://orcid.org/0000-0001-7328-0275","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, ChangSha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.4172,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83405145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3747","last_page":"3757"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9983000159263611,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146941423416138},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5294886231422424},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5292983055114746},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48610758781433105},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.4362516701221466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43268880248069763},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35407572984695435},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22688031196594238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15106555819511414},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11892244219779968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146941423416138},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5294886231422424},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5292983055114746},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48610758781433105},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4362516701221466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43268880248069763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35407572984695435},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22688031196594238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15106555819511414},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11892244219779968}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671741","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671741","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671741","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671741","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671741","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401856733.pdf","grobid_xml":"https://content.openalex.org/works/W4401856733.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1480538416","https://openalex.org/W1982032418","https://openalex.org/W2577326063","https://openalex.org/W2795069772","https://openalex.org/W2907492528","https://openalex.org/W3007260230","https://openalex.org/W3011253634","https://openalex.org/W3089028909","https://openalex.org/W3102100346","https://openalex.org/W3112288498","https://openalex.org/W3124474911","https://openalex.org/W3129166376","https://openalex.org/W3164731060","https://openalex.org/W3175030727","https://openalex.org/W3183048323","https://openalex.org/W3201888171","https://openalex.org/W3212755951","https://openalex.org/W4206984109","https://openalex.org/W4224926219","https://openalex.org/W4287826515","https://openalex.org/W4287865413","https://openalex.org/W4304014903","https://openalex.org/W4306178504","https://openalex.org/W4309978318","https://openalex.org/W4312808544","https://openalex.org/W4385568413","https://openalex.org/W4386083082","https://openalex.org/W4387125275","https://openalex.org/W4387968412","https://openalex.org/W6847458731"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2391251536","https://openalex.org/W2362198218","https://openalex.org/W1982750869","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W2114770238","https://openalex.org/W2113077220","https://openalex.org/W2375008505","https://openalex.org/W2016188383"],"abstract_inverted_index":{"This":[0],"paper":[1],"delves":[2],"into":[3],"the":[4,23,45,89,94,139,142,161],"confidence":[5,39,61,147,174],"calibration":[6,84,122,148],"in":[7,22,29,40,71,76,127,145,153,172,183],"prediction":[8,57,98],"when":[9],"using":[10],"Graph":[11,112],"Neural":[12,113],"Networks":[13],"(GNNs),":[14],"which":[15],"has":[16],"emerged":[17],"as":[18],"a":[19,106,120],"notable":[20],"challenge":[21],"field.":[24],"Despite":[25],"their":[26,41],"remarkable":[27],"capabilities":[28],"processing":[30],"graph-structured":[31],"data,":[32],"GNNs":[33],"are":[34],"prone":[35],"to":[36,52,59,69,118,159],"exhibit":[37],"lower":[38],"predictions":[42],"than":[43],"what":[44],"actual":[46],"accuracy":[47],"warrants.":[48],"Recent":[49],"advances":[50],"attempt":[51],"address":[53],"this":[54,64,77,102],"by":[55],"minimizing":[56],"entropy":[58],"enhance":[60],"levels.":[62],"However,":[63],"method":[65],"inadvertently":[66],"risks":[67],"leading":[68],"over-confidence":[70,124],"model":[72],"predictions.":[73],"Our":[74],"investigation":[75],"work":[78],"reveals":[79],"that":[80],"most":[81],"existing":[82],"GNN":[83],"methods":[85],"predominantly":[86],"focus":[87],"on":[88],"highest":[90],"logit,":[91],"thereby":[92],"neglecting":[93],"entire":[95],"spectrum":[96],"of":[97,141],"probabilities.":[99],"To":[100,130],"alleviate":[101],"limitation,":[103],"we":[104,136],"introduce":[105],"novel":[107],"framework":[108,144],"called":[109],"Balanced":[110],"Calibrated":[111],"Network":[114],"(BCGNN),":[115],"specifically":[116],"designed":[117],"establish":[119],"balanced":[121],"between":[123],"and":[125,149,175,181],"under-confidence":[126],"GNNs'":[128],"prediction.":[129,154],"theoretically":[131],"support":[132],"our":[133,168],"proposed":[134],"method,":[135],"further":[137],"demonstrate":[138],"mechanism":[140],"BCGNN":[143],"effective":[146],"significant":[150],"trustworthiness":[151],"improvement":[152],"We":[155],"conduct":[156],"extensive":[157],"experiments":[158],"examine":[160],"developed":[162],"framework.":[163],"The":[164],"empirical":[165],"results":[166],"show":[167],"method's":[169],"superior":[170],"performance":[171],"predictive":[173],"trustworthiness,":[176],"affirming":[177],"its":[178],"practical":[179],"applicability":[180],"effectiveness":[182],"real-world":[184],"scenarios.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}