{"id":"https://openalex.org/W4385764513","doi":"https://doi.org/10.24963/ijcai.2023/257","title":"Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention","display_name":"Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764513","doi":"https://doi.org/10.24963/ijcai.2023/257"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/257","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/257","pdf_url":"https://www.ijcai.org/proceedings/2023/0257.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0257.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100357107","display_name":"Hongjun Wang","orcid":"https://orcid.org/0000-0001-6736-6566"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongjun Wang","raw_affiliation_strings":["Southern University of Science and Technology","Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047124423","display_name":"Jiyuan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyuan Chen","raw_affiliation_strings":["Southern University of Science and Technology","Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":["Microsoft Research","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032254756","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-1456-4216"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Microsoft Research","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101308414","display_name":"Han Shi","orcid":"https://orcid.org/0009-0003-0223-1769"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Shi Han","raw_affiliation_strings":["Microsoft Research","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046856721","display_name":"Xuan Song","orcid":"https://orcid.org/0000-0003-4042-7888"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Song","raw_affiliation_strings":["Southern University of Science and Technology","Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100357107"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.994,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80710663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2315","last_page":"2323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9623000025749207,"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":0.7492192387580872},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.6071739792823792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5667858123779297},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.549430251121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5416377782821655},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.516472578048706},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5155596733093262},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4827112853527069},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4194006323814392},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4158611297607422},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2884618043899536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7492192387580872},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.6071739792823792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5667858123779297},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.549430251121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5416377782821655},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.516472578048706},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5155596733093262},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4827112853527069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4194006323814392},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4158611297607422},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2884618043899536},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/257","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/257","pdf_url":"https://www.ijcai.org/proceedings/2023/0257.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/257","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/257","pdf_url":"https://www.ijcai.org/proceedings/2023/0257.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764513.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1509628846","https://openalex.org/W2132984949","https://openalex.org/W2516809705","https://openalex.org/W2552071645","https://openalex.org/W2577918148","https://openalex.org/W2606780347","https://openalex.org/W2787740662","https://openalex.org/W2883803180","https://openalex.org/W2916106175","https://openalex.org/W2945856670","https://openalex.org/W2952915411","https://openalex.org/W2962711740","https://openalex.org/W2963241951","https://openalex.org/W2963639956","https://openalex.org/W2963757395","https://openalex.org/W2963907629","https://openalex.org/W2964015378","https://openalex.org/W2964321699","https://openalex.org/W2995471443","https://openalex.org/W2996084050","https://openalex.org/W3005644236","https://openalex.org/W3035065454","https://openalex.org/W3094452565","https://openalex.org/W3097300053","https://openalex.org/W3100078588","https://openalex.org/W3122063025","https://openalex.org/W3128443161","https://openalex.org/W3129247927","https://openalex.org/W3153880451","https://openalex.org/W3156681329","https://openalex.org/W3160872503","https://openalex.org/W3172402898","https://openalex.org/W3187966659","https://openalex.org/W3196261868","https://openalex.org/W3211394146","https://openalex.org/W4225646704","https://openalex.org/W4280513732","https://openalex.org/W4280559560","https://openalex.org/W4286795917","https://openalex.org/W4286893067","https://openalex.org/W4287126238","https://openalex.org/W4287754915","https://openalex.org/W4287757758","https://openalex.org/W4288089072","https://openalex.org/W4288358813","https://openalex.org/W4289389616","https://openalex.org/W4290948450","https://openalex.org/W4297733535","https://openalex.org/W4300830895","https://openalex.org/W4303683958","https://openalex.org/W4307074454","https://openalex.org/W4321276816","https://openalex.org/W4382239972","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W4389995241","https://openalex.org/W4320149722","https://openalex.org/W3213655484"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,30],"witnessed":[3],"the":[4,61,72,81,88,137],"great":[5],"potential":[6],"of":[7,17,48,63,75,85,127],"attention":[8,76,86,98,135],"mechanism":[9],"in":[10,117],"graph":[11],"representation":[12],"learning.":[13],"However,":[14],"while":[15],"variants":[16],"attention-based":[18,115],"GNNs":[19,116],"are":[20,37],"setting":[21],"new":[22,57],"benchmarks":[23],"for":[24,71,112],"numerous":[25],"real-world":[26],"datasets,":[27],"recent":[28],"works":[29],"pointed":[31],"out":[32],"that":[33],"their":[34],"induced":[35],"attentions":[36],"less":[38],"robust":[39],"and":[40,91,149],"generalizable":[41],"against":[42],"noisy":[43],"graphs":[44],"due":[45],"to":[46,65,87,96,100,141],"lack":[47],"direct":[49,82],"supervision.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,79],"present":[55],"a":[56,67,109,124,145],"framework":[58],"which":[59],"utilizes":[60],"tool":[62],"causality":[64],"provide":[66],"powerful":[68],"supervision":[69],"signal":[70],"learning":[73],"process":[74],"functions.":[77],"Specifically,":[78],"estimate":[80],"causal":[83],"effect":[84,95],"final":[89],"prediction,":[90],"then":[92],"maximize":[93],"such":[94],"guide":[97],"attending":[99],"more":[101],"meaningful":[102],"neighbors.":[103],"Our":[104],"method":[105],"can":[106],"serve":[107],"as":[108],"plug-and-play":[110],"module":[111],"any":[113],"canonical":[114],"an":[118],"end-to-end":[119],"fashion.":[120],"Extensive":[121],"experiments":[122],"on":[123],"wide":[125],"range":[126],"benchmark":[128],"datasets":[129],"illustrated":[130],"that,":[131],"by":[132],"directly":[133],"supervising":[134],"functions,":[136],"model":[138],"is":[139],"able":[140],"converge":[142],"faster":[143],"with":[144],"clearer":[146],"decision":[147],"boundary,":[148],"thus":[150],"yields":[151],"better":[152],"performances.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}