{"id":"https://openalex.org/W2985323229","doi":"https://doi.org/10.1145/3357384.3358121","title":"Additive Explanations for Anomalies Detected from Multivariate Temporal Data","display_name":"Additive Explanations for Anomalies Detected from Multivariate Temporal Data","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2985323229","doi":"https://doi.org/10.1145/3357384.3358121","mag":"2985323229"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014197053","display_name":"Ioana Giurgiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ioana Giurgiu","raw_affiliation_strings":["IBM Research - Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069005357","display_name":"Anika Schumann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126328","display_name":"IBM Research - Zurich","ror":"https://ror.org/02js37d36","country_code":"CH","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126328"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anika Schumann","raw_affiliation_strings":["IBM Research - Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210126328"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210126328"],"apc_list":null,"apc_paid":null,"fwci":1.9683,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90579986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2245","last_page":"2248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.860659122467041},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7888371348381042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6888513565063477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6622589230537415},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6453403830528259},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6004915237426758},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5718480944633484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.534890353679657},{"id":"https://openalex.org/keywords/multivariate-analysis","display_name":"Multivariate analysis","score":0.4662182927131653},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.46351754665374756},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.43662041425704956},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.42273759841918945},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38985660672187805},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3881615698337555},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32910317182540894},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10230058431625366},{"id":"https://openalex.org/keywords/paleontology","display_name":"Paleontology","score":0.07191964983940125}],"concepts":[{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.860659122467041},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7888371348381042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6888513565063477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622589230537415},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6453403830528259},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6004915237426758},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5718480944633484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.534890353679657},{"id":"https://openalex.org/C38180746","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate analysis","level":2,"score":0.4662182927131653},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.46351754665374756},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.43662041425704956},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.42273759841918945},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38985660672187805},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3881615698337555},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32910317182540894},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10230058431625366},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.07191964983940125},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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:10.1145/3357384.3358121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2053744708","https://openalex.org/W2516809705","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2618851150","https://openalex.org/W2900906990","https://openalex.org/W2913556461","https://openalex.org/W2949780682","https://openalex.org/W2964094285"],"related_works":["https://openalex.org/W4210405904","https://openalex.org/W4312467842","https://openalex.org/W3123344745","https://openalex.org/W3186512740","https://openalex.org/W3185547778","https://openalex.org/W3044458868","https://openalex.org/W3192727092","https://openalex.org/W2292254049","https://openalex.org/W4310034804","https://openalex.org/W4285276855"],"abstract_inverted_index":{"Detecting":[0],"anomalies":[1,49,83],"from":[2,85],"high-dimensional":[3],"multivariate":[4,86],"temporal":[5],"data":[6],"is":[7,51],"challenging,":[8],"because":[9],"of":[10,39],"the":[11,48,96],"non-linear,":[12],"complex":[13],"relationships":[14,30],"between":[15,34],"signals.":[16],"Recently,":[17],"deep":[18],"learning":[19],"methods":[20],"based":[21],"on":[22,113],"autoencoders":[23],"have":[24],"been":[25],"shown":[26],"to":[27,81,101],"capture":[28],"these":[29],"and":[31,36,104,117,128],"accurately":[32],"discern":[33],"normal":[35],"abnormal":[37],"patterns":[38],"behavior,":[40],"even":[41],"in":[42,79],"fully":[43],"unsupervised":[44],"scenarios.":[45],"However,":[46],"validating":[47],"detected":[50,84],"difficult":[52],"without":[53],"additional":[54],"explanations.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,94,120],"extend":[60],"SHAP":[61],"--":[62,75],"a":[63,90],"unified":[64],"framework":[65],"for":[66,72,125],"providing":[67],"additive":[68],"explanations,":[69],"previously":[70],"applied":[71],"supervised":[73],"models":[74],"with":[76,89],"influence":[77],"weighting,":[78],"order":[80],"explain":[82],"time":[87],"series":[88],"GRU-based":[91],"autoencoder.":[92],"Namely,":[93],"extract":[95],"signals":[97],"that":[98,106,119],"contribute":[99],"most":[100],"an":[102],"anomaly":[103],"those":[105],"counteract":[107],"it.":[108],"We":[109],"evaluate":[110],"our":[111],"approach":[112],"two":[114],"use":[115],"cases":[116],"show":[118],"can":[121],"generate":[122],"insightful":[123],"explanations":[124],"both":[126],"single":[127],"multiple":[129],"anomalies.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-10-10T00:00:00"}