{"id":"https://openalex.org/W7138010702","doi":"https://doi.org/10.1609/aaai.v40i25.39231","title":"GCIB: Causal Intervention Guided Graph Information Bottleneck Framework","display_name":"GCIB: Causal Intervention Guided Graph Information Bottleneck Framework","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138010702","doi":"https://doi.org/10.1609/aaai.v40i25.39231"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i25.39231","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i25.39231","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i25.39231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076573337","display_name":"Hangyuan Du","orcid":"https://orcid.org/0000-0002-1294-5832"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hangyuan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691625","display_name":"Rong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041443460","display_name":"Lixin Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixin Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067305206","display_name":"Gaoxia Jiang","orcid":"https://orcid.org/0000-0002-2343-1132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaoxia Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647863","display_name":"Liang Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129717510","display_name":"Wenjian Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjian Wang","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"25","first_page":"20905","last_page":"20913"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9404000043869019,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9404000043869019,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.011300000362098217,"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":0.007600000128149986,"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/bottleneck","display_name":"Bottleneck","score":0.7634999752044678},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6597999930381775},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.6588000059127808},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.567799985408783},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4431999921798706},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.40639999508857727},{"id":"https://openalex.org/keywords/dependency-graph","display_name":"Dependency graph","score":0.4025000035762787}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7634999752044678},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.6588000059127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068000197410583},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.567799985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49639999866485596},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i25.39231","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i25.39231","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39231","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i25.39231","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i25.39231","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0,83,151],"neural":[1],"networks":[2],"(GNNs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7],"in":[8,50,68,167],"a":[9,47,89],"broad":[10],"spectrum":[11],"of":[12,92,101,122,183],"fields,":[13],"but":[14],"always":[15],"suffer":[16],"from":[17,110],"the":[18,35,56,69,82,93,111,120,128,141,181],"generalization":[19,75,170],"problem":[20],"when":[21],"confronted":[22],"with":[23,52,119],"out-of-distribution":[24],"(OOD)":[25],"scenarios.":[26],"Information":[27,85],"bottleneck":[28],"(IB)":[29],"principle,":[30],"which":[31,98],"endeavors":[32],"to":[33,45,72],"learn":[34],"minimally":[36],"sufficient":[37],"representations":[38,152],"for":[39,95,144],"downstream":[40],"tasks,":[41],"has":[42],"been":[43],"shown":[44],"be":[46],"promising":[48],"strategy":[49],"dealing":[51],"this":[53,78,137],"problem.":[54],"However,":[55],"IB-based":[57],"methods":[58],"do":[59],"not":[60],"inherently":[61],"distinguish":[62],"between":[63],"causal":[64,90,108,124,130,159],"and":[65,106,132,146,177],"non-causal":[66],"parts":[67],"graph,":[70],"leading":[71],"underperforming":[73],"OOD":[74,169],"ability.":[76,171],"In":[77],"paper,":[79],"we":[80,115,139],"develop":[81],"Causal":[84],"Bottleneck":[86],"(GCIB)":[87],"framework,":[88],"extension":[91],"IB":[94,118],"graph":[96,117,164],"data,":[97],"is":[99],"capable":[100],"jointly":[102],"compressing":[103],"abundant":[104],"information":[105,160],"capturing":[107],"dependency":[109],"input":[112],"graph.":[113],"Specifically,":[114],"endow":[116],"ability":[121],"maintaining":[123],"control":[125],"by":[126,154],"incorporating":[127],"underlying":[129],"structure":[131],"introducing":[133],"intervention":[134],"operation.":[135],"On":[136],"basis,":[138],"formulate":[140],"learning":[142],"objective":[143],"GCIB":[145,155,184],"present":[147],"its":[148],"specific":[149],"implementation.":[150],"learned":[153],"can":[156],"effectively":[157],"preserve":[158],"that":[161],"fundamentally":[162],"determines":[163],"properties,":[165],"resulting":[166],"outstanding":[168],"Extensive":[172],"experiments":[173],"on":[174],"both":[175],"synthetic":[176],"real-world":[178],"datasets":[179],"demonstrate":[180],"superiority":[182],"over":[185],"state-of-the-art":[186],"baselines.":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}