{"id":"https://openalex.org/W3081364375","doi":"https://doi.org/10.1145/3394486.3403066","title":"GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction","display_name":"GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3081364375","doi":"https://doi.org/10.1145/3394486.3403066","mag":"3081364375"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403066","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403066","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039440984","display_name":"Thai Le","orcid":"https://orcid.org/0000-0001-9632-6870"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thai Le","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048500","display_name":"Suhang Wang","orcid":"https://orcid.org/0000-0003-3448-4878"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhang Wang","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405086","display_name":"Dongwon Lee","orcid":"https://orcid.org/0000-0001-8371-7629"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongwon Lee","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"238","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9927999973297119,"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":0.983299970626831,"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":0.7860443592071533},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7053842544555664},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6451973915100098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6253786683082581},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5067220330238342},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.5035261511802673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4971597492694855},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41044655442237854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860443592071533},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7053842544555664},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6451973915100098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6253786683082581},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5067220330238342},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5035261511802673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4971597492694855},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41044655442237854},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403066","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"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403066","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403066","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403066","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":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1152168623","display_name":null,"funder_award_id":"1742702,1820609,1909702,1915801,1934782","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1726689462","display_name":"Developing and Evaluating Fraud Informatics Curriculum among Institutions in the Appalachian Region","funder_award_id":"1820609","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2466292668","display_name":"Vertical Search Engine and Graph Homomorphism for Enhancing the Cybersecurity Workforce","funder_award_id":"1934782","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3867987763","display_name":"EAGER: Training Computers and Humans to Detect Misinformation by Combining Computational and Theoretical Analysis","funder_award_id":"1742702","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5382995392","display_name":"EAGER: SaTC: Early-Stage Interdisciplinary Collaboration: Modeling Memory Illusion for Predicting Trust in Online Information","funder_award_id":"1915801","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7366345995","display_name":"III: Small: Collaborative Research: Effective Labeled Data Generation via Generative Adversarial Learning","funder_award_id":"1909702","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3081364375.pdf","grobid_xml":"https://content.openalex.org/works/W3081364375.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W333550619","https://openalex.org/W1533861849","https://openalex.org/W1566965859","https://openalex.org/W1585743408","https://openalex.org/W1661871015","https://openalex.org/W1849277567","https://openalex.org/W1961009203","https://openalex.org/W2024834471","https://openalex.org/W2047182010","https://openalex.org/W2153803020","https://openalex.org/W2243397390","https://openalex.org/W2282821441","https://openalex.org/W2510508396","https://openalex.org/W2561981131","https://openalex.org/W2765204106","https://openalex.org/W2772723798","https://openalex.org/W2796837256","https://openalex.org/W2897834873","https://openalex.org/W2921573932","https://openalex.org/W2945587318","https://openalex.org/W2950772592","https://openalex.org/W2962824341","https://openalex.org/W2962941306","https://openalex.org/W2963698230","https://openalex.org/W3105926539","https://openalex.org/W3120740533","https://openalex.org/W4298235707","https://openalex.org/W4300954432","https://openalex.org/W4324128313"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W2081494945","https://openalex.org/W4248383205","https://openalex.org/W2389053294","https://openalex.org/W1970893504","https://openalex.org/W4234745530","https://openalex.org/W4312071518"],"abstract_inverted_index":{"Despite":[0],"the":[1,5,15,25,32,112],"recent":[2],"development":[3],"in":[4,40],"topic":[6],"of":[7,17,27,114,129,136,187],"explainable":[8],"AI/ML":[9],"for":[10,81],"image":[11],"and":[12,36,60,66,95,132,143,155,169],"text":[13],"data,":[14],"majority":[16],"current":[18],"solutions":[19],"are":[20,34,39,62],"not":[21,165],"suitable":[22],"to":[23,101,141,175],"explain":[24],"prediction":[26,89],"neural":[28,77],"network":[29,78],"models":[30],"when":[31],"datasets":[33,128],"tabular":[35,82],"their":[37],"features":[38,137],"high-dimensional":[41],"vectorized":[42],"formats.":[43],"To":[44],"mitigate":[45],"this":[46],"limitation,":[47],"therefore,":[48],"we":[49],"borrow":[50],"two":[51],"notable":[52],"ideas":[53],"(i.e.,":[54],"\"explanation":[55,61],"by":[56],"intervention\"":[57],"from":[58,64,139],"causality":[59],"contrastive\"":[63],"philosophy)":[65],"propose":[67],"a":[68,87,97],"novel":[69],"solution,":[70],"named":[71],"as":[72,90,104,177,179],"GRACE,":[73],"that":[74,160,186],"better":[75],"explains":[76],"models'":[79],"predictions":[80],"datasets.":[83],"In":[84],"particular,":[85],"given":[86],"model's":[88],"label":[91],"X,":[92],"GRACE":[93,145],"intervenes":[94],"generates":[96],"minimally-modified":[98],"contrastive":[99],"sample":[100],"be":[102],"classified":[103],"Y,":[105],"with":[106,146],"an":[107],"intuitive":[108,168],"textual":[109],"explanation,":[110],"answering":[111],"question":[113],"\"Why":[115],"X":[116],"rather":[117],"than":[118,185],"Y?\"":[119],"We":[120],"carry":[121],"out":[122],"comprehensive":[123],"experiments":[124],"using":[125],"eleven":[126],"public":[127],"different":[130,150],"scales":[131],"domains":[133],"(e.g.,":[134],"#":[135],"ranges":[138],"5":[140],"216)":[142],"compare":[144],"competing":[147],"baselines":[148],"on":[149],"measures:":[151],"fidelity,":[152],"conciseness,":[153],"info-gain,":[154],"influence.":[156],"The":[157],"user-studies":[158],"show":[159],"our":[161],"generated":[162],"explanation":[163],"is":[164],"only":[166],"more":[167,181],"easy-to-understand":[170],"but":[171],"also":[172],"facilitates":[173],"end-users":[174],"make":[176],"much":[178],"60%":[180],"accurate":[182],"post-explanation":[183],"decisions":[184],"Lime.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}