{"id":"https://openalex.org/W7160954915","doi":"https://doi.org/10.48550/arxiv.2605.10242","title":"When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection","display_name":"When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160954915","doi":"https://doi.org/10.48550/arxiv.2605.10242"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10242","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.10242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135958974","display_name":"Wei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001991004","display_name":"Hezhe Qiao","orcid":"https://orcid.org/0000-0003-3511-0528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Hezhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102834541","display_name":"Kailai Zhang","orcid":"https://orcid.org/0000-0002-9062-0865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kailai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135951511","display_name":"Zaisheng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zaisheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071034640","display_name":"Yu-Ming Shang","orcid":"https://orcid.org/0000-0003-2903-4223"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Yu-Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002341443","display_name":"Xiangling Fu","orcid":"https://orcid.org/0000-0002-1492-2829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xiangling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9757000207901001,"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":0.9757000207901001,"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":0.007000000216066837,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/discriminative-model","display_name":"Discriminative model","score":0.8403000235557556},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7537999749183655},{"id":"https://openalex.org/keywords/normality","display_name":"Normality","score":0.7246999740600586},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6158000230789185},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5960999727249146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5795999765396118},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5162000060081482},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.39959999918937683}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8403000235557556},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.7246999740600586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769999861717224},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5960999727249146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10242","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.10242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10242","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7602457404136658}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"tabular":[1,182],"anomaly":[2,76],"detection":[3,190],"methods":[4],"typically":[5],"learn":[6],"feature":[7],"patterns":[8,22],"from":[9,20,81],"normal":[10,46,88,131],"samples":[11,17,154],"during":[12,25],"training":[13,37],"and":[14,34,89],"subsequently":[15],"identify":[16],"that":[18,185],"deviate":[19],"these":[21,94],"as":[23],"anomalies":[24],"testing.":[26],"However,":[27],"in":[28],"practical":[29],"scenarios,":[30],"the":[31,61,79,149,174],"limited":[32],"scale":[33],"diversity":[35],"of":[36,45],"data":[38,73],"often":[39],"lead":[40],"to":[41,70,127,167],"an":[42],"incomplete":[43],"characterization":[44],"patterns.":[47],"While":[48],"test-time":[49,58],"adaptation":[50,69,102,144],"offers":[51],"a":[52,99,115,129,135,162],"remedy,":[53],"its":[54,84],"isolated":[55],"focus":[56],"on":[57,180],"optimization":[59],"ignores":[60],"critical":[62],"synergy":[63],"with":[64],"training-phase":[65],"learning.":[66],"Furthermore,":[67],"indiscriminate":[68],"unlabeled":[71],"test":[72],"inevitably":[74],"triggers":[75],"contamination,":[77],"preventing":[78],"model":[80,150],"fully":[82],"realizing":[83],"discriminative":[85,176],"capability":[86],"between":[87],"anomalous":[90,157],"samples.":[91],"To":[92],"address":[93],"issues,":[95],"we":[96],"propose":[97],"RTTAD,":[98],"Risk-aware":[100],"Test-time":[101],"method":[103],"for":[104,143],"unsupervised":[105],"Tabular":[106],"Anomaly":[107],"Detection.":[108],"RTTAD":[109,186],"holistically":[110],"tackles":[111],"normality":[112],"shifts":[113],"via":[114],"synergistic":[116],"two-stage":[117],"mechanism.":[118],"During":[119,133],"training,":[120],"collaborative":[121],"dual-task":[122],"learning":[123],"captures":[124],"multi-level":[125],"representations":[126],"establish":[128],"robust":[130],"prior.":[132],"testing,":[134],"Test-Time":[136],"Contrastive":[137],"Learning":[138],"(TTCL)":[139],"module":[140],"explicitly":[141],"accounts":[142],"risk":[145],"by":[146],"selectively":[147],"updating":[148],"using":[151],"high-confidence":[152],"pseudo-normal":[153],"while":[155],"constraining":[156],"ones.":[158],"Additionally,":[159],"TTCL":[160],"incorporates":[161],"k-nearest":[163],"neighbor-based":[164],"contrastive":[165],"objective":[166],"refine":[168],"embedding":[169],"distributions,":[170],"thereby":[171],"further":[172],"enhancing":[173],"model's":[175],"capacity.":[177],"Extensive":[178],"experiments":[179],"15":[181],"datasets":[183],"demonstrate":[184],"achieves":[187],"state-of-the-art":[188],"overall":[189],"performance.":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}