{"id":"https://openalex.org/W7138288291","doi":"https://doi.org/10.1609/aaai.v40i17.38522","title":"Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detection","display_name":"Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138288291","doi":"https://doi.org/10.1609/aaai.v40i17.38522"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i17.38522","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38522","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i17.38522","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031046113","display_name":"Minseo Kang","orcid":"https://orcid.org/0009-0004-6828-115X"},"institutions":[{"id":"https://openalex.org/I165677929","display_name":"Sungshin Women's University","ror":"https://ror.org/0500xzf72","country_code":"KR","type":"education","lineage":["https://openalex.org/I165677929"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Minseo Kang","raw_affiliation_strings":["Sungshin Women's University"],"affiliations":[{"raw_affiliation_string":"Sungshin Women's University","institution_ids":["https://openalex.org/I165677929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129670067","display_name":"Seunghwan Park","orcid":null},"institutions":[{"id":"https://openalex.org/I165507594","display_name":"Kangwon National University","ror":"https://ror.org/01mh5ph17","country_code":"KR","type":"education","lineage":["https://openalex.org/I165507594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghwan Park","raw_affiliation_strings":["Kangwon National University"],"affiliations":[{"raw_affiliation_string":"Kangwon National University","institution_ids":["https://openalex.org/I165507594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129722304","display_name":"Dongha Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I165677929","display_name":"Sungshin Women's University","ror":"https://ror.org/0500xzf72","country_code":"KR","type":"education","lineage":["https://openalex.org/I165677929"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongha Kim","raw_affiliation_strings":["Sungshin Women's University"],"affiliations":[{"raw_affiliation_string":"Sungshin Women's University","institution_ids":["https://openalex.org/I165677929"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031046113"],"corresponding_institution_ids":["https://openalex.org/I165677929"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50214133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"17","first_page":"15000","last_page":"15008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9843999743461609,"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":0.9843999743461609,"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":0.00139999995008111,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0013000000035390258,"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/outlier","display_name":"Outlier","score":0.7847999930381775},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6054999828338623},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.604200005531311},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5791000127792358},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5249999761581421},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41920000314712524}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7847999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6929000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866000294685364},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26829999685287476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i17.38522","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38522","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i17.38522","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i17.38522","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Outlier":[0],"detection":[1],"(OD)":[2],"aims":[3],"to":[4,54,102,119,152,177],"identify":[5,179],"abnormal":[6],"instances,":[7],"known":[8,42],"as":[9,43],"outliers":[10,84,90],"or":[11,20,88],"anomalies,":[12],"by":[13],"learning":[14,101],"typical":[15],"patterns":[16,57],"of":[17,126],"normal":[18],"data,":[19],"inliers.":[21],"Performing":[22],"OD":[23,227],"under":[24],"an":[25],"unsupervised":[26,70],"regime--without":[27],"any":[28],"information":[29],"about":[30],"anomalous":[31],"instances":[32],"in":[33,145,173],"the":[34,44,76,116,137,154,174,185,196],"training":[35],"data--is":[36],"challenging.":[37],"A":[38],"recently":[39],"observed":[40],"phenomenon,":[41],"inlier-memorization":[45],"(IM)":[46],"effect,":[47,139],"where":[48],"deep":[49],"generative":[50],"models":[51],"(DGMs)":[52],"tend":[53],"memorize":[55],"inlier":[56,157,200],"during":[58],"early":[59],"training,":[60,207],"provides":[61],"a":[62,110,130,142,165,191],"promising":[63],"signal":[64],"for":[65],"distinguishing":[66],"outliers.":[67],"However,":[68],"existing":[69],"approaches":[71],"that":[72,113,133,195,219],"rely":[73],"solely":[74],"on":[75,214],"IM":[77,117,138],"effect":[78,118],"still":[79],"struggle":[80],"when":[81,89],"inliers":[82],"and":[83,107,135,140,158,169,182],"are":[85,150],"not":[86,221],"well-separated":[87],"form":[91],"dense":[92],"clusters.":[93],"To":[94],"address":[95],"these":[96],"limitations,":[97],"we":[98,163],"incorporate":[99],"active":[100,226],"selectively":[103],"acquire":[104],"informative":[105,180],"labels,":[106],"propose":[108,164],"IMBoost,":[109],"novel":[111,166],"framework":[112],"explicitly":[114],"reinforces":[115],"improve":[120],"outlier":[121,159,204],"detection.":[122],"Our":[123],"method":[124],"consists":[125],"two":[127],"stages:":[128],"1)":[129],"warm-up":[131],"phase":[132,144,176],"induces":[134],"promotes":[136],"2)":[141],"polarization":[143,175],"which":[146],"actively":[147],"queried":[148],"samples":[149,181],"used":[151],"maximize":[153],"discrepancy":[155],"between":[156],"scores.":[160],"In":[161],"particular,":[162],"query":[167],"strategy":[168],"tailored":[170],"loss":[171],"function":[172],"effectively":[178],"fully":[183],"leverage":[184],"limited":[186],"labeling":[187],"budget.":[188],"We":[189],"provide":[190],"theoretical":[192],"analysis":[193],"showing":[194],"IMBoost":[197,220],"consistently":[198],"decreases":[199],"risk":[201,205],"while":[202],"increasing":[203],"throughout":[206],"thereby":[208],"amplifying":[209],"their":[210],"separation.":[211],"Extensive":[212],"experiments":[213],"diverse":[215],"benchmark":[216],"datasets":[217],"demonstrate":[218],"only":[222],"significantly":[223],"outperforms":[224],"state-of-the-art":[225],"methods":[228],"but":[229],"also":[230],"requires":[231],"substantially":[232],"less":[233],"computational":[234],"cost.":[235]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}