{"id":"https://openalex.org/W4384643953","doi":"https://doi.org/10.1145/3580305.3599435","title":"MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation","display_name":"MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4384643953","doi":"https://doi.org/10.1145/3580305.3599435"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107249265","display_name":"Jiaxing Zhang","orcid":"https://orcid.org/0009-0007-8031-661X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiaxing Zhang","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102761357","display_name":"Dongsheng Luo","orcid":"https://orcid.org/0000-0003-4192-0826"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongsheng Luo","raw_affiliation_strings":["Florida International University, Miami, FL, USA"],"affiliations":[{"raw_affiliation_string":"Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100777770","display_name":"Hua Wei","orcid":"https://orcid.org/0000-0002-3735-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua Wei","raw_affiliation_strings":["NJIT & Arizona State University, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NJIT & Arizona State University, Newark, NJ, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107249265"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":3.4566,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93931526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3286","last_page":"3296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9973000288009644,"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":0.982699990272522,"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":0.7489452362060547},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7462486028671265},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6356333494186401},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.47219929099082947},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.45356130599975586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44560375809669495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43561992049217224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.396464467048645},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.10903200507164001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489452362060547},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7462486028671265},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6356333494186401},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47219929099082947},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.45356130599975586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44560375809669495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43561992049217224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.396464467048645},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.10903200507164001},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580305.3599435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2307.07832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.07832","pdf_url":"https://arxiv.org/pdf/2307.07832","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":"doi:10.1145/3580305.3599435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580305.3599435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580305.3599435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2172159137","display_name":null,"funder_award_id":"2153311","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6755165505","display_name":null,"funder_award_id":"award","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384643953.pdf","grobid_xml":"https://content.openalex.org/works/W4384643953.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2056562706","https://openalex.org/W2116341502","https://openalex.org/W2187089797","https://openalex.org/W2765407302","https://openalex.org/W2931367569","https://openalex.org/W2972317931","https://openalex.org/W3012562343","https://openalex.org/W3092206109","https://openalex.org/W3094193403","https://openalex.org/W3105259638","https://openalex.org/W3116637551","https://openalex.org/W3121087702","https://openalex.org/W3169350676","https://openalex.org/W3174022889","https://openalex.org/W3186377753","https://openalex.org/W3201342094","https://openalex.org/W3207981989","https://openalex.org/W4212890525","https://openalex.org/W4224326164","https://openalex.org/W4289236186","https://openalex.org/W4289751568","https://openalex.org/W4290944300","https://openalex.org/W4307823382","https://openalex.org/W4321795178","https://openalex.org/W4385404463","https://openalex.org/W6607489081","https://openalex.org/W6784958482"],"related_works":["https://openalex.org/W2622284819","https://openalex.org/W1504394672","https://openalex.org/W3089381707","https://openalex.org/W4285254085","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103","https://openalex.org/W2304083841"],"abstract_inverted_index":{"Graph":[0,89],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,28],"received":[5],"increasing":[6],"attention":[7],"due":[8],"to":[9,12,31,38,103,123,139],"their":[10,18],"ability":[11],"learn":[13],"from":[14],"graph-structured":[15],"data.":[16],"However,":[17],"predictions":[19],"are":[20],"often":[21],"not":[22],"interpretable.":[23],"Post-hoc":[24],"instance-level":[25],"explanation":[26,69],"methods":[27,36],"been":[29],"proposed":[30,145,160],"understand":[32],"GNN":[33],"predictions.":[34],"These":[35],"seek":[37],"discover":[39],"substructures":[40],"that":[41,94],"explain":[42],"the":[43,57,60,104,109,125,141,163],"prediction":[44],"behavior":[45],"of":[46,59,143,157],"a":[47,87,96,114,120,154],"trained":[48],"GNN.":[49],"In":[50],"this":[51,83],"paper,":[52],"we":[53,85,112],"shed":[54],"light":[55],"on":[56,74,133],"existence":[58],"distribution":[61,126,164],"shifting":[62,127,165],"issue":[63],"in":[64,72],"existing":[65,149],"methods,":[66],"which":[67,100],"affects":[68],"quality,":[70],"particularly":[71],"applications":[73],"real-life":[75],"datasets":[76,138],"with":[77,119],"tight":[78],"decision":[79],"boundaries.":[80],"To":[81],"address":[82],"issue,":[84],"introduce":[86],"generalized":[88,110],"Information":[90],"Bottleneck":[91],"(GIB)":[92],"form":[93],"includes":[95],"label-independent":[97],"graph":[98,115],"variable,":[99],"is":[101],"equivalent":[102],"vanilla":[105],"GIB.":[106],"Driven":[107],"by":[108],"GIB,":[111],"propose":[113],"mixup":[116,146],"method,":[117],"MixupExplainer,":[118],"theoretical":[121],"guarantee":[122],"resolve":[124],"issue.":[128,166],"We":[129,151],"conduct":[130],"extensive":[131],"experiments":[132],"both":[134],"synthetic":[135],"and":[136],"real-world":[137],"validate":[140],"effectiveness":[142],"our":[144,159],"approach":[147,161],"over":[148],"approaches.":[150],"also":[152],"provide":[153],"detailed":[155],"analysis":[156],"how":[158],"alleviates":[162]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-07-19T00:00:00"}