{"id":"https://openalex.org/W4401862786","doi":"https://doi.org/10.1145/3637528.3672003","title":"Fast Unsupervised Deep Outlier Model Selection with Hypernetworks","display_name":"Fast Unsupervised Deep Outlier Model Selection with Hypernetworks","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401862786","doi":"https://doi.org/10.1145/3637528.3672003"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3672003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3672003","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3672003","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3672003","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026875500","display_name":"Xueying Ding","orcid":"https://orcid.org/0000-0001-6338-6068"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xueying Ding","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057711796","display_name":"Yue Zhao","orcid":"https://orcid.org/0000-0003-3401-4921"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001634795","display_name":"Leman Akoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leman Akoglu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026875500"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.7205,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75721536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"585","last_page":"596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9927999973297119,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659895181655884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5989956855773926},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5501081943511963},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5318557620048523},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.5164787769317627},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.42175066471099854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37819868326187134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33035874366760254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659895181655884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989956855773926},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5501081943511963},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5318557620048523},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.5164787769317627},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.42175066471099854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37819868326187134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33035874366760254}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3672003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3672003","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3672003","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3672003","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3672003","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3672003","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401862786.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W110258791","https://openalex.org/W1992276041","https://openalex.org/W2070996757","https://openalex.org/W2081131942","https://openalex.org/W2089217417","https://openalex.org/W2097714558","https://openalex.org/W2192203593","https://openalex.org/W2282861635","https://openalex.org/W2556522401","https://openalex.org/W2743138268","https://openalex.org/W2963445059","https://openalex.org/W3006197067","https://openalex.org/W3023012876","https://openalex.org/W3039137796","https://openalex.org/W3089028909","https://openalex.org/W3129166376","https://openalex.org/W3175514463","https://openalex.org/W3178985214","https://openalex.org/W3206604724","https://openalex.org/W3211291089","https://openalex.org/W4211116959","https://openalex.org/W4249717689","https://openalex.org/W4286895466","https://openalex.org/W4383199656","https://openalex.org/W6757844995"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729","https://openalex.org/W4381571012"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"based":[3],"Outlier":[4],"Detection":[5],"(DOD)":[6],"has":[7],"seen":[8],"a":[9,27,66,117,137,170],"recent":[10],"surge":[11],"of":[12,47,69,89,96,107,127],"attention":[13],"thanks":[14],"to":[15,50,87,101,113,150,168],"the":[16,45,53,60,97,105,128],"many":[17,146],"advances":[18],"in":[19,104],"deep":[20],"learning.":[21],"In":[22,132,157],"this":[23],"paper,":[24],"we":[25],"consider":[26],"critical-yet-understudied":[28],"challenge":[29],"with":[30,166,176,196],"unsupervised":[31],"DOD,":[32],"that":[33,64,121,140,188],"is,":[34],"effective":[35],"hyperparameter":[36],"(HP)":[37],"tuning/model":[38],"selection.":[39],"While":[40],"several":[41],"prior":[42],"work":[43],"report":[44],"sensitivity":[46],"OD":[48,164,185],"models":[49,63,148],"HP":[51],"settings,":[52],"issue":[54],"is":[55,112],"ever":[56],"so":[57],"critical":[58],"for":[59,74,145],"modern":[61],"DOD":[62,76,130,147],"exhibit":[65],"long":[67],"list":[68],"HPs.":[70],"We":[71],"introduce":[72],"HYPER":[73,134,189],"tuning":[75],"models,":[77],"tackling":[78],"two":[79],"fundamental":[80],"challenges:":[81],"(1)":[82],"validation":[83,172],"without":[84],"supervision":[85],"(due":[86,100],"lack":[88],"labeled":[90],"outliers),":[91],"and":[92,115],"(2)":[93],"efficient":[94],"search":[95],"HP/model":[98],"space":[99],"exponential":[102],"growth":[103],"number":[106],"HPs).":[108],"A":[109],"key":[110],"idea":[111],"design":[114],"train":[116,169],"novel":[118],"hypernetwork":[119],"(HN)":[120],"maps":[122],"HPs":[123],"onto":[124],"optimal":[125],"weights":[126,144],"main":[129],"model.":[131],"turn,":[133],"capitalizes":[135],"on":[136,162,183],"single":[138],"HN":[139,179],"can":[141],"dynamically":[142],"generate":[143],"(corresponding":[149],"varying":[151],"HPs),":[152],"which":[153],"offers":[154],"significant":[155,197],"speed-up.":[156],"addition,":[158],"it":[159],"employs":[160],"meta-learning":[161],"historical":[163],"tasks":[165,186],"labels":[167],"proxy":[171],"function,":[173],"likewise":[174],"trained":[175],"our":[177],"proposed":[178],"efficiently.":[180],"Extensive":[181],"experiments":[182],"different":[184],"show":[187],"achieves":[190],"competitive":[191],"performance":[192],"against":[193],"8":[194],"baselines":[195],"efficiency":[198],"gains.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}