{"id":"https://openalex.org/W4381329328","doi":"https://doi.org/10.1145/3589302","title":"GoodCore: Data-effective and Data-efficient Machine Learning through Coreset Selection over Incomplete Data","display_name":"GoodCore: Data-effective and Data-efficient Machine Learning through Coreset Selection over Incomplete Data","publication_year":2023,"publication_date":"2023-06-13","ids":{"openalex":"https://openalex.org/W4381329328","doi":"https://doi.org/10.1145/3589302"},"language":"en","primary_location":{"id":"doi:10.1145/3589302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589302","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589302","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101797040","display_name":"Chengliang Chai","orcid":"https://orcid.org/0000-0001-8080-5594"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengliang Chai","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8080-5594","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017484177","display_name":"Jiabin Liu","orcid":"https://orcid.org/0009-0004-3653-5987"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabin Liu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3653-5987","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0003-2832-0295","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739546","display_name":"Ju Fan","orcid":"https://orcid.org/0000-0003-4729-9903"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Fan","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4729-9903","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089467202","display_name":"Dongjing Miao","orcid":"https://orcid.org/0000-0001-9370-7088"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjing Miao","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-9370-7088","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092212559","display_name":"Jiayi Wang","orcid":"https://orcid.org/0000-0002-9700-9751"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9700-9751","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614732","display_name":"Yuyu Luo","orcid":"https://orcid.org/0000-0001-9530-3327"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyu Luo","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9530-3327","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1398-0621","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3329,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97318957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9854000210762024,"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":0.7395600080490112},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.533263087272644},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5169429183006287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4593626856803894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34249359369277954},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06890428066253662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395600080490112},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.533263087272644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5169429183006287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593626856803894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34249359369277954},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06890428066253662},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589302","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3589302","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589302","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589302","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G5652550493","display_name":null,"funder_award_id":"61632016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6110938807","display_name":null,"funder_award_id":"62102215, 62122090, 62072461, 61925205, 61632016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6880998225","display_name":null,"funder_award_id":"62122090, 62072461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7169141996","display_name":null,"funder_award_id":"62102215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G831406350","display_name":null,"funder_award_id":"61925205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8539191751","display_name":"\u4f17\u5305\u6570\u636e\u5e93\u7684\u57fa\u7840\u7406\u8bba\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61632016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G957598617","display_name":null,"funder_award_id":"62102215, 62122090, 62072461","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381329328.pdf","grobid_xml":"https://content.openalex.org/works/W4381329328.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W650854417","https://openalex.org/W1781481323","https://openalex.org/W1977185509","https://openalex.org/W1985239372","https://openalex.org/W1985258161","https://openalex.org/W2064186732","https://openalex.org/W2077518845","https://openalex.org/W2102720558","https://openalex.org/W2164187405","https://openalex.org/W2402007731","https://openalex.org/W2428834396","https://openalex.org/W2548122763","https://openalex.org/W2581441561","https://openalex.org/W2776050171","https://openalex.org/W2798990443","https://openalex.org/W2803403013","https://openalex.org/W2888359544","https://openalex.org/W2889357608","https://openalex.org/W2897574832","https://openalex.org/W2943501111","https://openalex.org/W2951565755","https://openalex.org/W2952029797","https://openalex.org/W2997919412","https://openalex.org/W3012492726","https://openalex.org/W3030674916","https://openalex.org/W3030764521","https://openalex.org/W3032629661","https://openalex.org/W3032848711","https://openalex.org/W3034856749","https://openalex.org/W3035623224","https://openalex.org/W3045786285","https://openalex.org/W3085684300","https://openalex.org/W3105982656","https://openalex.org/W3147796863","https://openalex.org/W3174906424","https://openalex.org/W3175777295","https://openalex.org/W3176502563","https://openalex.org/W3176803066","https://openalex.org/W3196436244","https://openalex.org/W3213578841","https://openalex.org/W4210394794","https://openalex.org/W4224310326","https://openalex.org/W4226163509","https://openalex.org/W4243565423","https://openalex.org/W4245179829","https://openalex.org/W4253785454","https://openalex.org/W4283367762","https://openalex.org/W4289533982","https://openalex.org/W4292070111","https://openalex.org/W4312929313","https://openalex.org/W4361793154","https://openalex.org/W6772013027"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4313488044","https://openalex.org/W3209574120","https://openalex.org/W4312192474","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Given":[0],"a":[1,10,24,49,54,160,220],"dataset":[2],"with":[3,166,223,258],"incomplete":[4,16,115,128,144,164,187],"data":[5,17,30,36,59,70,129,145,165],"(e.g.,":[6],"missing":[7],"values),":[8],"training":[9,83,203],"machine":[11,134],"learning":[12],"model":[13,40,76,106,142,170],"over":[14,127,163],"the":[15,29,35,39,43,58,64,68,72,82,97,101,122,143,155,171,177,186,209,251],"requires":[18,23,48],"two":[19],"steps.":[20],"First,":[21],"it":[22,47],"data-effective":[25,131],"step":[26,51],"that":[27,52,63,237],"cleans":[28],"in":[31,78],"order":[32,79],"to":[33,80,95,141],"improve":[34,81],"quality":[37,41],"(and":[38],"on":[42,67,190],"cleaned":[44],"data).":[45],"Second,":[46],"data-efficient":[50,133],"selects":[53,194],"core":[55],"subset":[56],"of":[57,124,179,185,255],"(called":[60],"coreset)":[61],"such":[62],"trained":[65],"models":[66],"entire":[69],"and":[71,132,218,253],"coreset":[73,113,125,162,198,212],"have":[74,104],"similar":[75],"quality,":[77,107],"efficiency.":[84],"The":[85,136],"first-data-effective-then-data-efficient":[86],"methods":[87,103,236],"are":[88,93],"too":[89],"costly,":[90],"because":[91,108],"they":[92,109],"expensive":[94],"clean":[96],"whole":[98],"data;":[99],"while":[100],"first-data-efficient-then-data-effective":[102],"low":[105,167,259],"cannot":[110],"select":[111],"high-quality":[112,148],"for":[114,130,146],"data.":[116,188],"In":[117],"this":[118,151],"paper,":[119],"we":[120,153,175,232],"investigate":[121],"problem":[123],"selection":[126,213],"learning.":[135],"essential":[137],"challenge":[138],"is":[139],"how":[140],"selecting":[147,159],"coreset.":[149],"To":[150,169,227],"end,":[152],"propose":[154,219,234],"GoodCore":[156,193,229],"framework":[157,257],"towards":[158],"good":[161],"cost.":[168,260],"unknown":[172],"complete":[173],"data,":[174],"utilize":[176],"combinations":[178],"possible":[180,183,191],"repairs":[181],"as":[182],"worlds":[184],"Based":[189],"worlds,":[192],"an":[195,224],"expected":[196,210],"optimal":[197,211],"through":[199],"gradient":[200],"approximation":[201,225],"without":[202],"ML":[204],"models.":[205],"We":[206],"formally":[207],"define":[208],"problem,":[214],"prove":[215],"its":[216],"NP-hardness,":[217],"greedy":[221],"algorithm":[222],"ratio.":[226],"make":[228],"more":[230],"efficient,":[231],"further":[233],"optimization":[235],"incorporate":[238],"human-in-the-loop":[239],"imputation":[240,243],"or":[241],"automatic":[242],"method":[244],"into":[245],"our":[246,256],"framework.":[247],"Experimental":[248],"results":[249],"show":[250],"effectiveness":[252],"efficiency":[254]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}