{"id":"https://openalex.org/W3035625410","doi":"https://doi.org/10.1145/3394486.3403071","title":"Adversarial Infidelity Learning for Model Interpretation","display_name":"Adversarial Infidelity Learning for Model Interpretation","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3035625410","doi":"https://doi.org/10.1145/3394486.3403071","mag":"3035625410"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403071","pdf_url":null,"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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.05379","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112582835","display_name":"Jian Liang","orcid":"https://orcid.org/0000-0003-3890-1894"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Liang","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090022501","display_name":"Bing Bai","orcid":"https://orcid.org/0000-0002-6953-1948"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Bai","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081211506","display_name":"Yuren Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuren Cao","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102906188","display_name":"Kun Bai","orcid":"https://orcid.org/0000-0002-3773-5364"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Bai","raw_affiliation_strings":["Tencent, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455768","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0001-9459-9461"},"institutions":[{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Weill Cornell Medicine, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Weill Cornell Medicine, New York, NY, USA","institution_ids":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112582835"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.6458,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87209642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9995999932289124,"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":0.9995999932289124,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9944999814033508,"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":0.9879999756813049,"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":0.8060789108276367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6696323752403259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6609287261962891},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.595860481262207},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5321399569511414},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5053994655609131},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4606037735939026},{"id":"https://openalex.org/keywords/identifiability","display_name":"Identifiability","score":0.45832809805870056},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4146421253681183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3641842007637024},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.15735584497451782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060789108276367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6696323752403259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6609287261962891},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.595860481262207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5321399569511414},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5053994655609131},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4606037735939026},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.45832809805870056},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4146421253681183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3641842007637024},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.15735584497451782},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403071","pdf_url":null,"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:2006.05379","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.05379","pdf_url":"https://arxiv.org/pdf/2006.05379","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":"pmh:oai:arXiv.org:2006.05379","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.05379","pdf_url":"https://arxiv.org/pdf/2006.05379","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1901129140","https://openalex.org/W2063046703","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2113459411","https://openalex.org/W2123045220","https://openalex.org/W2282821441","https://openalex.org/W2402144811","https://openalex.org/W2516809705","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2612445135","https://openalex.org/W2614653677","https://openalex.org/W2618851150","https://openalex.org/W2626639386","https://openalex.org/W2726296976","https://openalex.org/W2750384547","https://openalex.org/W2750779823","https://openalex.org/W2770398803","https://openalex.org/W2810518847","https://openalex.org/W2891612330","https://openalex.org/W2898138693","https://openalex.org/W2901232217","https://openalex.org/W2903544706","https://openalex.org/W2913039310","https://openalex.org/W2917322567","https://openalex.org/W2924718922","https://openalex.org/W2945544216","https://openalex.org/W2949725973","https://openalex.org/W2950112733","https://openalex.org/W2951025380","https://openalex.org/W2951306478","https://openalex.org/W2952622013","https://openalex.org/W2953073956","https://openalex.org/W2953384591","https://openalex.org/W2962790223","https://openalex.org/W2962851944","https://openalex.org/W2962862931","https://openalex.org/W2963365341","https://openalex.org/W2963382180","https://openalex.org/W2964121592","https://openalex.org/W2964296416","https://openalex.org/W2966869984","https://openalex.org/W2970013628","https://openalex.org/W2970155250","https://openalex.org/W2970242004","https://openalex.org/W2970447476","https://openalex.org/W2970658946","https://openalex.org/W2970670424","https://openalex.org/W2970726176","https://openalex.org/W2971201880","https://openalex.org/W2980096013","https://openalex.org/W2990222711","https://openalex.org/W2996061341","https://openalex.org/W3009950094","https://openalex.org/W3012815759","https://openalex.org/W3022179901","https://openalex.org/W3138819813","https://openalex.org/W4239072543","https://openalex.org/W4288088628","https://openalex.org/W4293861706","https://openalex.org/W4297775537","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2724847603","https://openalex.org/W2034041141","https://openalex.org/W2184661725","https://openalex.org/W112856298","https://openalex.org/W2573470972","https://openalex.org/W2105626102","https://openalex.org/W2131038454","https://openalex.org/W4240568257","https://openalex.org/W2900187352","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Model":[0],"interpretation":[1,33,196],"is":[2,34,230],"essential":[3],"in":[4],"data":[5,49],"mining":[6],"and":[7,19,84,167,186,215,222],"knowledge":[8],"discovery.":[9],"It":[10],"can":[11,176],"help":[12,177],"understand":[13],"the":[14,22,48,54,57,91,100,103,118,122,125,143,157,179,220],"intrinsic":[15],"model":[16,23,32,55,74,82,127],"working":[17],"mechanism":[18,154,175],"check":[20],"if":[21],"has":[24],"undesired":[25],"characteristics.":[26],"A":[27],"popular":[28],"way":[29],"of":[30,44,102,124,224],"performing":[31],"Instance-wise":[35],"Feature":[36],"Selection":[37],"(IFS),":[38],"which":[39,106],"provides":[40],"an":[41,129,134,149],"importance":[42],"score":[43],"each":[45],"feature":[46],"representing":[47],"samples":[50],"to":[51,97,132,155,201,218],"explain":[52],"how":[53],"generates":[56],"specific":[58],"output.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,88,120,147,170,189],"propose":[64,148],"a":[65,109,203],"Model-agnostic":[66],"Effective":[67],"Efficient":[68],"Direct":[69],"(MEED)":[70],"IFS":[71],"framework":[72,192],"for":[73,113],"interpretation,":[75],"mitigating":[76],"concerns":[77],"about":[78],"sanity,":[79],"combinatorial":[80],"shortcuts,":[81],"identifiability,":[83],"information":[85],"transmission.":[86],"Also,":[87],"focus":[89],"on":[90,137],"following":[92],"setting:":[93],"using":[94],"selected":[95,184],"features":[96,185],"directly":[98],"predict":[99],"output":[101,123],"given":[104,126],"model,":[105],"serves":[107],"as":[108,128,198],"primary":[110],"evaluation":[111,208,217],"metric":[112],"model-interpretation":[114],"methods.":[115],"Apart":[116],"from":[117],"features,":[119],"involve":[121],"additional":[130],"input":[131],"learn":[133,142,178],"explainer":[135],"based":[136],"more":[138],"accurate":[139],"information.":[140],"To":[141],"explainer,":[144],"besides":[145],"fidelity,":[146],"Adversarial":[150],"Infidelity":[151],"Learning":[152],"(AIL)":[153],"boost":[156],"explanation":[158],"learning":[159],"by":[160,193,212],"screening":[161],"relatively":[162],"unimportant":[163],"features.":[164],"Through":[165],"theoretical":[166],"experimental":[168],"analysis,":[169],"show":[171],"that":[172],"our":[173,191,225],"AIL":[174],"desired":[180],"conditional":[181],"distribution":[182],"between":[183],"targets.":[187],"Moreover,":[188],"extend":[190],"integrating":[194],"efficient":[195],"methods":[197],"proper":[199],"priors":[200],"provide":[202],"warm":[204],"start.":[205],"Comprehensive":[206],"empirical":[207],"results":[209],"are":[210],"provided":[211],"quantitative":[213],"metrics":[214],"human":[216],"demonstrate":[219],"effectiveness":[221],"superiority":[223],"proposed":[226],"method.":[227],"Our":[228],"code":[229],"publicly":[231],"available":[232],"online":[233],"at":[234],"https://github.com/langlrsw/MEED.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}