{"id":"https://openalex.org/W3033892090","doi":"https://doi.org/10.1145/3394486.3403085","title":"XGNN: Towards Model-Level Explanations of Graph Neural Networks","display_name":"XGNN: Towards Model-Level Explanations of Graph Neural Networks","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3033892090","doi":"https://doi.org/10.1145/3394486.3403085","mag":"3033892090"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403085","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403085","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & 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/10.1145/3394486.3403085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hao Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Yuan","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiliang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiliang Tang","raw_affiliation_strings":["Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xia Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Hu","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shuiwang Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuiwang Ji","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":16.8564,"has_fulltext":true,"cited_by_count":256,"citation_normalized_percentile":{"value":0.99350823,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"430","last_page":"438"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9988999962806702,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9988999962806702,"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/T11273","display_name":"Advanced Graph Neural Networks","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9923999905586243,"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/graph","display_name":"Graph","score":0.5713000297546387},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5022000074386597},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4115000069141388},{"id":"https://openalex.org/keywords/directed-graph","display_name":"Directed graph","score":0.3361999988555908},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3199000060558319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390999913215637},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5022000074386597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2962999939918518}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403085","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403085","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.02587","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02587","pdf_url":"https://arxiv.org/pdf/2006.02587","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:10.1145/3394486.3403085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403085","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403085","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1088727777","display_name":"Collaborative Research: ABI Innovation: Towards Computational Exploration of Large-Scale Neuro-Morphological Datasets","funder_award_id":"2028361","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1436348175","display_name":null,"funder_award_id":"IIS-1845081","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2972935627","display_name":null,"funder_award_id":"IIS-1714741, IIS-1715940","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3412060240","display_name":"CAREER: Real-World Networks: Modeling and Analysis of Signed Networks with Positive and Negative Links","funder_award_id":"1845081","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3423907736","display_name":null,"funder_award_id":"DBI-2028361","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3834216676","display_name":null,"funder_award_id":"N66001-17-2-4031","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5495925939","display_name":"III: Small: Unsupervised Feature Selection in the Era of Big Data","funder_award_id":"1714741","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5700204612","display_name":null,"funder_award_id":"IIS-190","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6020892857","display_name":null,"funder_award_id":"IIS-1714741, IIS-1715940, IIS-1845081","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7110045","display_name":null,"funder_award_id":"IIS-1714741","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7773032749","display_name":"III: Small: Collaborative Research: A General Feature Learning Framework for Dynamic Attributed Networks","funder_award_id":"1715940","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"},{"id":"https://openalex.org/G8783789473","display_name":null,"funder_award_id":"IIS-1715940","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G879600408","display_name":"III: Medium: Collaborative Research: Towards Effective Interpretation of Deep Learning: Prediction, Representation, Modeling and Utilization","funder_award_id":"1900990","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"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3033892090.pdf","grobid_xml":"https://content.openalex.org/works/W3033892090.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W1932198206","https://openalex.org/W2056562706","https://openalex.org/W2061425021","https://openalex.org/W2295107390","https://openalex.org/W2557449848","https://openalex.org/W2606462007","https://openalex.org/W2788919350","https://openalex.org/W2904479140","https://openalex.org/W2962858109","https://openalex.org/W2963169753","https://openalex.org/W2963233086","https://openalex.org/W2963639956","https://openalex.org/W2964268978","https://openalex.org/W4229494842"],"related_works":[],"abstract_inverted_index":{"Graphs":[0],"neural":[1],"networks":[2],"(GNNs)":[3],"learn":[4],"node":[5],"features":[6],"by":[7,89],"aggregating":[8],"and":[9,29,40,75,171,181],"combining":[10],"neighbor":[11],"information,":[12],"which":[13],"have":[14],"achieved":[15],"promising":[16],"performance":[17],"on":[18,145,168,198],"many":[19],"graph":[20,92,98,110,122,135,156],"tasks.":[21],"However,":[22],"GNNs":[23,65,80,88],"are":[24],"mostly":[25],"treated":[26],"as":[27,61,112],"black-boxes":[28],"lack":[30],"human":[31],"intelligible":[32],"explanations.":[33],"Thus,":[34],"they":[35],"cannot":[36,49],"be":[37,50,164],"fully":[38],"trusted":[39],"used":[41],"in":[42],"certain":[43,102],"application":[44],"domains":[45],"if":[46],"GNN":[47],"models":[48],"explained.":[51],"In":[52,82,151],"this":[53],"work,":[54],"we":[55,84,153],"propose":[56,85],"a":[57,91,101,113,140],"novel":[58],"approach,":[59],"known":[60],"XGNN,":[62],"to":[63,86,126,158,163,200],"interpret":[64],"at":[66],"the":[67,96,105,109,121,131,148,160,183,192,202],"model-level.":[68],"Our":[69],"approach":[70],"can":[71,195],"provide":[72,196],"high-level":[73],"insights":[74],"generic":[76],"understanding":[77],"of":[78,104],"how":[79,125,199],"work.":[81],"particular,":[83],"explain":[87],"training":[90],"generator":[93,123,136],"so":[94],"that":[95,175,191],"generated":[97,161,193],"patterns":[99],"maximize":[100],"prediction":[103],"model.":[106],"We":[107],"formulate":[108],"generation":[111],"reinforcement":[114],"learning":[115],"task,":[116],"where":[117],"for":[118],"each":[119],"step,":[120],"predicts":[124],"add":[127],"an":[128],"edge":[129],"into":[130],"current":[132],"graph.":[133],"The":[134],"is":[137],"trained":[138,149,184,203],"via":[139],"policy":[141],"gradient":[142],"method":[143],"based":[144],"information":[146],"from":[147],"GNNs.":[150,185,204],"addition,":[152],"incorporate":[154],"several":[155],"rules":[157],"encourage":[159],"graphs":[162,194],"valid.":[165],"Experimental":[166],"results":[167,189],"both":[169],"synthetic":[170],"real-world":[172],"datasets":[173],"show":[174],"our":[176,187],"proposed":[177],"methods":[178],"help":[179],"understand":[180],"verify":[182],"Furthermore,":[186],"experimental":[188],"indicate":[190],"guidance":[197],"improve":[201]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":58},{"year":2024,"cited_by_count":67},{"year":2023,"cited_by_count":46},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-06-12T00:00:00"}