{"id":"https://openalex.org/W3187916661","doi":"https://doi.org/10.1109/tkde.2021.3103571","title":"Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory","display_name":"Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3187916661","doi":"https://doi.org/10.1109/tkde.2021.3103571","mag":"3187916661"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3103571","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3103571","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09511218.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09511218.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053742066","display_name":"Maximilian Toller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Maximilian Bernhard Toller","raw_affiliation_strings":["Know Center GmbH, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Know Center GmbH, Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003584509","display_name":"Bernhard C. Geiger","orcid":"https://orcid.org/0000-0003-3257-743X"},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard Claus Geiger","raw_affiliation_strings":["Know Center GmbH, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Know Center GmbH, Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014398832","display_name":"Roman Kern","orcid":"https://orcid.org/0000-0003-0202-6100"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Roman Kern","raw_affiliation_strings":["Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053742066"],"corresponding_institution_ids":["https://openalex.org/I4210088621"],"apc_list":null,"apc_paid":null,"fwci":0.42,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.6933958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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":1.0,"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":0.993399977684021,"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/T12391","display_name":"Artificial Immune Systems Applications","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/outlier","display_name":"Outlier","score":0.8164215087890625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311335802078247},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6513936519622803},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6467147469520569},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5873997807502747},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5490649938583374},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.547383725643158},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5444653034210205},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.524534285068512},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5209318995475769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.511419951915741},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3836343288421631}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.8164215087890625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311335802078247},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6513936519622803},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6467147469520569},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5873997807502747},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5490649938583374},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.547383725643158},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5444653034210205},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.524534285068512},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5209318995475769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.511419951915741},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3836343288421631},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2021.3103571","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3103571","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09511218.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2302.11234","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.11234","pdf_url":"https://arxiv.org/pdf/2302.11234","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/tkde.2021.3103571","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3103571","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09511218.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1534472752","display_name":null,"funder_award_id":"iDev40","funder_id":"https://openalex.org/F4320327207","funder_display_name":"Electronic Components and Systems for European Leadership"},{"id":"https://openalex.org/G2773297097","display_name":null,"funder_award_id":"783163","funder_id":"https://openalex.org/F4320327207","funder_display_name":"Electronic Components and Systems for European Leadership"},{"id":"https://openalex.org/G3729258792","display_name":null,"funder_award_id":"783163","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320327207","display_name":"Electronic Components and Systems for European Leadership","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187916661.pdf","grobid_xml":"https://content.openalex.org/works/W3187916661.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1607767822","https://openalex.org/W1673310716","https://openalex.org/W1880693368","https://openalex.org/W1965555277","https://openalex.org/W1972626687","https://openalex.org/W1978239142","https://openalex.org/W1989037929","https://openalex.org/W1990368529","https://openalex.org/W2019014808","https://openalex.org/W2026386905","https://openalex.org/W2029236670","https://openalex.org/W2029532007","https://openalex.org/W2036557187","https://openalex.org/W2040263621","https://openalex.org/W2041184937","https://openalex.org/W2066796814","https://openalex.org/W2067092965","https://openalex.org/W2079361215","https://openalex.org/W2083681515","https://openalex.org/W2099111195","https://openalex.org/W2110784166","https://openalex.org/W2119236027","https://openalex.org/W2122646361","https://openalex.org/W2140413822","https://openalex.org/W2143559571","https://openalex.org/W2144182447","https://openalex.org/W2148986322","https://openalex.org/W2166064672","https://openalex.org/W2282861635","https://openalex.org/W2395916081","https://openalex.org/W2434205482","https://openalex.org/W2478708596","https://openalex.org/W2592377938","https://openalex.org/W2621614835","https://openalex.org/W2731977498","https://openalex.org/W2756489700","https://openalex.org/W2773303230","https://openalex.org/W2783415626","https://openalex.org/W2803697594","https://openalex.org/W2884586244","https://openalex.org/W2888297916","https://openalex.org/W2894881080","https://openalex.org/W2902758299","https://openalex.org/W2910068345","https://openalex.org/W2919115771","https://openalex.org/W2945976633","https://openalex.org/W2949848919","https://openalex.org/W2962819609","https://openalex.org/W2990722563","https://openalex.org/W3208688400","https://openalex.org/W4231620004","https://openalex.org/W4239328607","https://openalex.org/W4242702158","https://openalex.org/W4255387915","https://openalex.org/W4297730339","https://openalex.org/W6637131181","https://openalex.org/W6659467978","https://openalex.org/W6747227044","https://openalex.org/W6751494907","https://openalex.org/W6758101687"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Rate-distortion":[0],"theory-based":[1],"outlier":[2,33],"detection":[3],"builds":[4],"upon":[5,98],"the":[6,41,70],"rationale":[7],"that":[8,49,76,94,105],"a":[9,74],"good":[10],"data":[11,48],"compression":[12],"will":[13],"encode":[14],"outliers":[15,99],"with":[16],"unique":[17,55],"symbols.":[18],"Based":[19],"on":[20],"this":[21],"rationale,":[22],"we":[23,92],"propose":[24,58],"Cluster":[25,64,95,106],"Purging,":[26,65],"which":[27],"is":[28],"an":[29,89],"extension":[30,36],"of":[31,43],"clustering-based":[32],"detection.":[34],"This":[35],"allows":[37],"one":[38,66],"to":[39,46,82],"assess":[40],"representivity":[42,78],"clusterings,":[44,103],"and":[45,104],"find":[47],"are":[50],"best":[51],"represented":[52],"by":[53],"individual":[54],"clusters.":[56],"We":[57],"two":[59],"efficient":[60],"algorithms":[61],"for":[62],"performing":[63],"being":[67],"parameter-free,":[68],"while":[69],"other":[71],"algorithm":[72],"has":[73],"parameter":[75],"controls":[77],"estimations,":[79],"allowing":[80],"it":[81],"be":[83],"tuned":[84],"in":[85],"supervised":[86],"setups.":[87],"In":[88],"experimental":[90],"evaluation,":[91],"show":[93],"Purging":[96,107],"improves":[97],"detected":[100],"from":[101],"raw":[102],"competes":[108],"strongly":[109],"against":[110],"state-of-the-art":[111],"alternatives.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2021-08-16T00:00:00"}