{"id":"https://openalex.org/W4403569927","doi":"https://doi.org/10.48550/arxiv.2410.09570","title":"GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks","display_name":"GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks","publication_year":2024,"publication_date":"2024-10-12","ids":{"openalex":"https://openalex.org/W4403569927","doi":"https://doi.org/10.48550/arxiv.2410.09570"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.09570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09570","pdf_url":"https://arxiv.org/pdf/2410.09570","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2410.09570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027933499","display_name":"Dingyi Zhuang","orcid":"https://orcid.org/0000-0003-3208-6016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Dingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233971","display_name":"Chonghe Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Chonghe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027813095","display_name":"Yunhan Zheng","orcid":"https://orcid.org/0000-0001-5114-7561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yunhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101998459","display_name":"Shenhao Wang","orcid":"https://orcid.org/0000-0003-4374-8193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023905102","display_name":"Jinhua Zhao","orcid":"https://orcid.org/0000-0002-1929-7583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jinhua","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/T11948","display_name":"Machine Learning in Materials Science","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9642999768257141,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9638000130653381,"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/T10320","display_name":"Neural Networks and Applications","score":0.9483000040054321,"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/scaling","display_name":"Scaling","score":0.7286249995231628},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6061406135559082},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5594169497489929},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4959958493709564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4953969717025757},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46167421340942383},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.4090746343135834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36479461193084717},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27666571736335754},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2181183397769928},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18649956583976746},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1844644546508789}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7286249995231628},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6061406135559082},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5594169497489929},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4959958493709564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4953969717025757},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46167421340942383},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.4090746343135834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36479461193084717},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27666571736335754},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2181183397769928},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18649956583976746},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1844644546508789},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.09570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09570","pdf_url":"https://arxiv.org/pdf/2410.09570","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.09570","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.09570","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.09570","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09570","pdf_url":"https://arxiv.org/pdf/2410.09570","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1798258033","display_name":null,"funder_award_id":"DE-EE0009211","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3114929365","display_name":null,"funder_award_id":"DE-EE0009211","funder_id":"https://openalex.org/F4320332360","funder_display_name":"Office of Energy Efficiency and Renewable Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320332360","display_name":"Office of Energy Efficiency and Renewable Energy","ror":"https://ror.org/02xznz413"},{"id":"https://openalex.org/F4320337919","display_name":"Office of Energy Efficiency","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403569927.pdf","grobid_xml":"https://content.openalex.org/works/W4403569927.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W2079781215","https://openalex.org/W4378770497","https://openalex.org/W4308245303","https://openalex.org/W2014033564","https://openalex.org/W2910573937","https://openalex.org/W4385571583","https://openalex.org/W4389519396","https://openalex.org/W2113438243"],"abstract_inverted_index":{"Graph":[0,70,87],"Neural":[1],"Networks":[2],"deliver":[3],"strong":[4],"classification":[5],"results":[6],"but":[7],"often":[8,52],"suffer":[9],"from":[10],"poor":[11],"calibration":[12,50,76,93,97,122],"performance,":[13],"leading":[14],"to":[15,42],"overconfidence":[16],"or":[17],"underconfidence.":[18],"This":[19],"is":[20,109,126],"particularly":[21],"problematic":[22],"in":[23],"high":[24],"stakes":[25],"applications":[26],"where":[27],"accurate":[28],"uncertainty":[29],"estimates":[30],"are":[31],"essential.":[32],"Existing":[33],"post":[34],"hoc":[35],"methods,":[36],"such":[37],"as":[38],"temperature":[39],"scaling,":[40],"fail":[41],"effectively":[43],"utilize":[44],"graph":[45],"structures,":[46],"while":[47],"current":[48],"GNN":[49,104],"methods":[51],"overlook":[53],"the":[54,66],"potential":[55],"of":[56,89,115],"leveraging":[57],"diverse":[58],"input":[59,80,118],"information":[60],"and":[61,81,113],"model":[62,82],"ensembles":[63],"jointly.":[64],"In":[65],"paper,":[67],"we":[68],"propose":[69],"Ensemble":[71],"Temperature":[72],"Scaling,":[73],"a":[74,86],"novel":[75],"framework":[77],"that":[78],"combines":[79],"ensemble":[83],"strategies":[84],"within":[85],"Mixture":[88],"Experts":[90],"archi":[91],"SOTA":[92],"techniques,":[94],"reducing":[95],"expected":[96],"error":[98],"by":[99],"25":[100],"percent":[101],"across":[102],"10":[103],"benchmark":[105],"datasets.":[106],"Additionally,":[107],"GETS":[108],"computationally":[110],"efficient,":[111],"scalable,":[112],"capable":[114],"selecting":[116],"effective":[117],"combinations":[119],"for":[120],"improved":[121],"performance.":[123],"The":[124],"implementation":[125],"available":[127],"via":[128],"Github.":[129]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}