{"id":"https://openalex.org/W3117974500","doi":"https://doi.org/10.1145/3430984.3431015","title":"Reliable Counterfactual Explanations for Autoencoder based Anomalies","display_name":"Reliable Counterfactual Explanations for Autoencoder based Anomalies","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3117974500","doi":"https://doi.org/10.1145/3430984.3431015","mag":"3117974500"},"language":"en","primary_location":{"id":"doi:10.1145/3430984.3431015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075293469","display_name":"Swastik Haldar","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Swastik Haldar","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017159940","display_name":"Philips George John","orcid":"https://orcid.org/0000-0003-2324-8933"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philips George John","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010368277","display_name":"Diptikalyan Saha","orcid":"https://orcid.org/0000-0002-1583-5479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diptikalyan Saha","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075293469"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9279,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81128319,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9975000023841858,"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":0.9975000023841858,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9941999912261963,"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":0.963699996471405,"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/autoencoder","display_name":"Autoencoder","score":0.9534320831298828},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9163508415222168},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7136949300765991},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6435565948486328},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6383880376815796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6035738587379456},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5779343843460083},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5501750111579895},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5389538407325745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43551206588745117},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4232946038246155},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.4114898145198822},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2778681516647339},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19470509886741638},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10642784833908081}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9534320831298828},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9163508415222168},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7136949300765991},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6435565948486328},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383880376815796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6035738587379456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5779343843460083},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5501750111579895},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5389538407325745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43551206588745117},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4232946038246155},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4114898145198822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2778681516647339},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19470509886741638},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10642784833908081},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3430984.3431015","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2127979711","https://openalex.org/W2130486630","https://openalex.org/W2154642048","https://openalex.org/W2282821441","https://openalex.org/W2557283755","https://openalex.org/W2618851150","https://openalex.org/W2743138268","https://openalex.org/W2766736793","https://openalex.org/W2889510677","https://openalex.org/W2891340972","https://openalex.org/W2893554781","https://openalex.org/W2909392392","https://openalex.org/W2932771740","https://openalex.org/W2945295328","https://openalex.org/W2945315238","https://openalex.org/W2962862931","https://openalex.org/W2963125461","https://openalex.org/W2963338867","https://openalex.org/W2973651390","https://openalex.org/W3101038122","https://openalex.org/W3104149808"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2905433371","https://openalex.org/W3186512740","https://openalex.org/W3017266184","https://openalex.org/W2918377632","https://openalex.org/W3202913553","https://openalex.org/W3194885736","https://openalex.org/W3046391934","https://openalex.org/W4363671829"],"abstract_inverted_index":{"Autoencoders":[0],"have":[1],"been":[2],"used":[3],"successfully":[4],"for":[5,96,114,151],"tackling":[6],"the":[7,61,69,103,108,119,159],"problem":[8,109],"of":[9,71,110,121,147,161,163],"anomaly":[10,85],"detection":[11],"in":[12,128],"an":[13,42,51,74,84,140],"unsupervised":[14],"setting,":[15],"and":[16,30,166],"are":[17],"often":[18],"known":[19],"to":[20,77,124,134,169],"give":[21],"better":[22],"results":[23],"than":[24,50],"traditional":[25],"approaches":[26],"such":[27],"as":[28,39,55,83],"clustering":[29],"subspace-based":[31],"(linear)":[32],"methods.":[33],"A":[34],"data":[35,81,132],"point":[36,82,133],"is":[37,48,86],"flagged":[38],"anomalous":[40,131],"by":[41,65],"autoencoder":[43,115,154],"if":[44],"its":[45],"reconstruction":[46],"loss":[47],"higher":[49],"appropriate":[52],"threshold.":[53],"However,":[54],"with":[56,101],"other":[57],"deep":[58],"learning":[59],"models,":[60],"increased":[62],"accuracy":[63],"offered":[64],"autoencoders":[66],"comes":[67],"at":[68],"cost":[70],"interpretability.":[72],"Explaining":[73],"autoencoder\u2019s":[75],"decision":[76],"flag":[78],"a":[79,90,97,129,144,152,164],"particular":[80],"greatly":[87],"important,":[88],"since":[89],"human-friendly":[91],"explanation":[92],"would":[93],"be":[94,125],"necessary":[95],"domain":[98],"expert":[99],"tasked":[100],"evaluating":[102],"model\u2019s":[104],"decisions.":[105],"We":[106,138,156],"consider":[107],"finding":[111],"counterfactual":[112,149,172],"explanations":[113,150],"anomalies,":[116],"which":[117],"address":[118],"question":[120],"what":[122],"needs":[123],"minimally":[126],"changed":[127],"given":[130,153],"make":[135],"it":[136],"non-anomalous.":[137],"present":[139,167],"algorithm":[141],"that":[142],"generates":[143],"diverse":[145],"set":[146],"proximate":[148],"anomaly.":[155],"also":[157],"introduce":[158],"notion":[160],"reliability":[162],"counterfactual,":[165],"techniques":[168],"find":[170],"reliable":[171],"explanations.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}