{"id":"https://openalex.org/W4290945397","doi":"https://doi.org/10.1145/3534678.3539476","title":"In Defense of Core-set: A Density-aware Core-set Selection for Active Learning","display_name":"In Defense of Core-set: A Density-aware Core-set Selection for Active Learning","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290945397","doi":"https://doi.org/10.1145/3534678.3539476"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539476","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014049239","display_name":"Yeachan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148704","display_name":"Deargen (South Korea)","ror":"https://ror.org/04j4j9405","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210148704"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeachan Kim","raw_affiliation_strings":["Deargen Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deargen Inc., Seoul, Republic of Korea","institution_ids":["https://openalex.org/I4210148704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102705831","display_name":"Bonggun Shin","orcid":"https://orcid.org/0000-0002-5133-0558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonggun Shin","raw_affiliation_strings":["Deargen USA, Inc., Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deargen USA, Inc., Atlanta, GA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6992,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.91953353,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"804","last_page":"812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9970999956130981,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9969000220298767,"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":0.7242827415466309},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6487513184547424},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.6474822163581848},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5844731330871582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382471084594727},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5167400240898132},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4901965260505676},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4722910523414612},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.3642224073410034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35973265767097473},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.12998393177986145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242827415466309},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6487513184547424},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6474822163581848},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5844731330871582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382471084594727},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5167400240898132},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4901965260505676},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4722910523414612},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3642224073410034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35973265767097473},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.12998393177986145},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539476","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539476","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W123226248","https://openalex.org/W1513874326","https://openalex.org/W1567003148","https://openalex.org/W1607198972","https://openalex.org/W1736726159","https://openalex.org/W1978633512","https://openalex.org/W2008989859","https://openalex.org/W2042932437","https://openalex.org/W2096623936","https://openalex.org/W2124244761","https://openalex.org/W2171671120","https://openalex.org/W2194775991","https://openalex.org/W2330006740","https://openalex.org/W2794002979","https://openalex.org/W2956371155","https://openalex.org/W2962849408","https://openalex.org/W2965858015","https://openalex.org/W2986514296","https://openalex.org/W3001679316","https://openalex.org/W3012994592","https://openalex.org/W3035499919","https://openalex.org/W3095809828","https://openalex.org/W3175994565"],"related_works":["https://openalex.org/W4287326768","https://openalex.org/W1556451512","https://openalex.org/W2393322642","https://openalex.org/W1555349535","https://openalex.org/W3131198547","https://openalex.org/W3099654136","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764"],"abstract_inverted_index":{"Active":[0],"learning":[1,22],"enables":[2],"the":[3,24,43,52,57,63,68,83,87,113,117,127,130,145,150,155,170,212],"efficient":[4],"construction":[5],"of":[6,26,89,129,172],"a":[7,19,121,159,190,203],"labeled":[8],"dataset":[9],"by":[10,50,108],"labeling":[11],"informative":[12,102,146],"samples":[13,49,71,103,132,136],"from":[14,138],"an":[15],"unlabeled":[16,131],"dataset.":[17],"In":[18,78],"real-world":[20],"active":[21],"scenario,":[23],"use":[25],"diversity-based":[27,45],"sampling":[28],"is":[29,42,195],"indispensable":[30],"because":[31],"there":[32],"are":[33,142],"many":[34],"redundant":[35],"or":[36],"highly":[37],"similar":[38],"samples.":[39,55],"Core-set":[40],"approach":[41,58,115],"promising":[44],"method":[46,65,208],"selecting":[47],"diverse":[48,135],"considering":[51],"distance":[53],"between":[54],"However,":[56],"poorly":[59],"performs":[60],"compared":[61],"to":[62,99,209],"uncertainty-based":[64],"that":[66,94,183,211],"selects":[67,134],"most":[69],"difficult":[70],"where":[72],"neural":[73],"models":[74],"reveal":[75],"low":[76],"confidence.":[77],"this":[79],"work,":[80],"we":[81,111,157,200],"analyze":[82],"feature":[84],"space":[85],"through":[86],"lens":[88],"density":[90,128,161],"and,":[91],"interestingly,":[92],"observe":[93],"locally":[95],"sparse":[96,139],"regions":[97,140],"tend":[98],"have":[100],"more":[101],"than":[104],"dense":[105],"regions.":[106,147],"Motivated":[107],"our":[109],"analysis,":[110],"empower":[112],"core-set":[114,123],"with":[116,219],"density-awareness":[118],"and":[119,133,177,180],"propose":[120],"density-aware":[122],"(DACS)":[124],"which":[125,141],"estimates":[126],"mainly":[137],"treated":[143],"as":[144],"To":[148],"reduce":[149],"computational":[151],"bottlenecks":[152],"in":[153,174,189],"estimating":[154],"density,":[156],"introduce":[158],"new":[160],"approximation":[162],"based":[163],"on":[164,198],"locality-sensitive":[165],"hashing.":[166],"Experimental":[167],"results":[168],"demonstrate":[169],"efficacy":[171],"DACS":[173,184,194],"both":[175],"classification":[176],"regression":[178],"tasks":[179],"specifically":[181],"show":[182,210],"can":[185,215],"produce":[186],"state-of-the-art":[187],"performance":[188],"practical":[191],"scenario.":[192],"Since":[193],"weakly":[196],"dependent":[197],"architectures,":[199],"also":[201],"present":[202],"simple":[204],"yet":[205],"effective":[206],"combination":[207],"existing":[213],"methods":[214],"be":[216],"beneficially":[217],"combined":[218],"DACS.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}