{"id":"https://openalex.org/W4409150271","doi":"https://doi.org/10.1145/3690624.3709294","title":"Distributional Prototype Learning for Out-of-distribution Detection","display_name":"Distributional Prototype Learning for Out-of-distribution Detection","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409150271","doi":"https://doi.org/10.1145/3690624.3709294"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709294","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3690624.3709294","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104387112","display_name":"Bo Peng","orcid":"https://orcid.org/0009-0009-0527-5322"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bo Peng","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675577","display_name":"Jie L\u00fc","orcid":"https://orcid.org/0000-0003-0690-4732"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Lu","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022901289","display_name":"Yonggang Zhang","orcid":"https://orcid.org/0000-0002-4080-7592"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yonggang Zhang","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062192039","display_name":"Guangquan Zhang","orcid":"https://orcid.org/0000-0003-3960-0583"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guangquan Zhang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087852871","display_name":"Zhen Fang","orcid":"https://orcid.org/0000-0003-0602-6255"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhen Fang","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104387112"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03192974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1104","last_page":"1114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.5192410945892334},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4369692802429199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5192410945892334},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4369692802429199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3690624.3709294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709294","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3690624.3709294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709294","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1932198206","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2129018774","https://openalex.org/W2194775991","https://openalex.org/W2732026016","https://openalex.org/W2797977484","https://openalex.org/W2884367402","https://openalex.org/W2988614387","https://openalex.org/W3034230713","https://openalex.org/W3036286896","https://openalex.org/W3045441084","https://openalex.org/W3126121388","https://openalex.org/W3163939464","https://openalex.org/W3202703311","https://openalex.org/W3203485920","https://openalex.org/W3213465214","https://openalex.org/W3214671430","https://openalex.org/W3214903388","https://openalex.org/W3216820735","https://openalex.org/W4224941647","https://openalex.org/W4283800429","https://openalex.org/W4306313214","https://openalex.org/W4312284582","https://openalex.org/W4312776478","https://openalex.org/W4317038436","https://openalex.org/W4386075650","https://openalex.org/W4386083133","https://openalex.org/W4386113255","https://openalex.org/W4402727435"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Out-of-distribution":[0],"(OOD)":[1],"detection":[2,80,228],"has":[3,236],"emerged":[4],"as":[5,44],"a":[6,45,96,169,194,207,238],"pivotal":[7],"approach":[8],"for":[9,20,77,132],"enhancing":[10],"the":[11,18,55,59,115,133,149,179,184,200,213,219],"reliability":[12],"of":[13,99,110,161,164,183,196,218],"machine":[14],"learning":[15,74,118,185],"models,":[16],"considering":[17],"potential":[19],"test":[21],"data":[22,32,40],"to":[23,103,120,127,140,156,212],"be":[24,203],"sampled":[25],"from":[26,29,54,193],"classes":[27],"disparate":[28],"in-distribution":[30],"(ID)":[31],"employed":[33],"during":[34],"model":[35,157],"training.":[36],"Detecting":[37],"those":[38,50],"OOD":[39,65,79,227,243],"is":[41,86,155],"typically":[42],"realized":[43],"distance":[46],"measurement":[47],"problem,":[48],"where":[49,82],"deviating":[51],"far":[52],"away":[53],"training":[56],"distribution":[57],"in":[58,73,206,241],"learned":[60],"feature":[61],"space":[62],"are":[63],"considered":[64],"samples.":[66],"Advanced":[67],"works":[68],"have":[69],"shown":[70],"great":[71],"success":[72],"with":[75,88,95,168],"prototypes":[76,100,163,192],"feature-based":[78],"methods,":[81],"each":[83,165],"ID":[84,166],"class":[85,167],"represented":[87],"single":[89],"or":[90],"multiple":[91],"prototypes.":[92],"However,":[93],"modeling":[94],"finite":[97],"number":[98,160],"would":[101],"fail":[102],"maximally":[104],"capture":[105],"intra-class":[106],"variations.":[107],"In":[108],"view":[109],"this,":[111],"this":[112],"paper":[113],"extends":[114],"existing":[116],"prototype-based":[117],"paradigm":[119],"an":[121,158],"infinite":[122,159],"setting.":[123],"This":[124],"motivates":[125],"us":[126],"design":[128],"two":[129],"feasible":[130],"formulations":[131],"Distributional":[134],"Prototype":[135],"Learning":[136],"(DPL)":[137],"objective,":[138],"where,":[139],"avoid":[141],"intractable":[142],"computation":[143],"and":[144],"exploding":[145],"parameters":[146],"caused":[147],"by":[148,190],"infinity":[150],"nature,":[151],"our":[152,233],"key":[153],"idea":[154],"discrete":[162],"class-wise":[170],"continuous":[171],"distribution.":[172],"We":[173,187],"theoretically":[174],"analyze":[175],"both":[176],"alternatives,":[177],"identifying":[178],"more":[180],"stable-converging":[181],"version":[182],"objective.":[186],"show":[188],"that,":[189],"sampling":[191],"mixture":[195],"class-conditioned":[197],"Gaussian":[198],"distributions,":[199],"objective":[201],"can":[202],"efficiently":[204],"computed":[205],"closed":[208],"form":[209],"without":[210],"resorting":[211],"computationally":[214],"expensive":[215],"Monte-Carlo":[216],"approximation":[217],"involved":[220],"expectation":[221],"terms.":[222],"Extensive":[223],"evaluations":[224],"across":[225],"mainstream":[226],"benchmarks":[229],"empirically":[230],"manifest":[231],"that":[232],"proposed":[234],"DPL":[235],"established":[237],"new":[239],"state-of-the-art":[240],"various":[242],"settings.":[244]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}