{"id":"https://openalex.org/W2970773487","doi":"https://doi.org/10.14778/3342263.3342637","title":"Efficient task-specific data valuation for nearest neighbor algorithms","display_name":"Efficient task-specific data valuation for nearest neighbor algorithms","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2970773487","doi":"https://doi.org/10.14778/3342263.3342637","mag":"2970773487"},"language":"en","primary_location":{"id":"doi:10.14778/3342263.3342637","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3342263.3342637","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","raw_type":"journal-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/A5032275274","display_name":"Ruoxi Jia","orcid":"https://orcid.org/0000-0001-9662-9556"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruoxi Jia","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023182736","display_name":"David Dao","orcid":"https://orcid.org/0000-0001-9096-7335"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Dao","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041191241","display_name":"Boxin Wang","orcid":"https://orcid.org/0000-0003-1084-4648"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxin Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041515151","display_name":"Frances Ann Hubis","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Frances Ann Hubis","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016955253","display_name":"Nezihe Merve G\u00fcrel","orcid":"https://orcid.org/0000-0002-4747-2406"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nezihe Merve Gurel","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["UIUC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013076652","display_name":"Costas J. Spanos","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Costas Spanos","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019426968","display_name":"Dawn Song","orcid":"https://orcid.org/0000-0001-9745-6802"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Song","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9996,"has_fulltext":false,"cited_by_count":161,"citation_normalized_percentile":{"value":0.97041271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"12","issue":"11","first_page":"1610","last_page":"1623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/approximation-algorithm","display_name":"Approximation algorithm","score":0.5811083316802979},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5757068395614624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5093656778335571},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5028159022331238},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.4771806001663208},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.4619119465351105},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.44807860255241394},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.417040079832077},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3338391184806824},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.27548840641975403},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.2648894786834717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18628984689712524},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.17690786719322205}],"concepts":[{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.5811083316802979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5757068395614624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5093656778335571},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5028159022331238},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.4771806001663208},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.4619119465351105},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.44807860255241394},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.417040079832077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3338391184806824},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.27548840641975403},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.2648894786834717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18628984689712524},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.17690786719322205},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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:10.14778/3342263.3342637","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3342263.3342637","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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 VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W61114007","https://openalex.org/W135566594","https://openalex.org/W1494851074","https://openalex.org/W1502916507","https://openalex.org/W1562353621","https://openalex.org/W1905312050","https://openalex.org/W1967833456","https://openalex.org/W2012833704","https://openalex.org/W2046116913","https://openalex.org/W2065504152","https://openalex.org/W2080217302","https://openalex.org/W2081434183","https://openalex.org/W2104106703","https://openalex.org/W2108598243","https://openalex.org/W2127807804","https://openalex.org/W2130695501","https://openalex.org/W2162006472","https://openalex.org/W2162670686","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2219547901","https://openalex.org/W2272515049","https://openalex.org/W2276615843","https://openalex.org/W2285990318","https://openalex.org/W2293940046","https://openalex.org/W2397770138","https://openalex.org/W2399897640","https://openalex.org/W2436401953","https://openalex.org/W2522099755","https://openalex.org/W2530395818","https://openalex.org/W2546440696","https://openalex.org/W2559655401","https://openalex.org/W2594166818","https://openalex.org/W2597603852","https://openalex.org/W2611914578","https://openalex.org/W2753705627","https://openalex.org/W2756922398","https://openalex.org/W2769835638","https://openalex.org/W2785776513","https://openalex.org/W2889110589","https://openalex.org/W2916829860","https://openalex.org/W2921189944","https://openalex.org/W2949170229","https://openalex.org/W2949780682","https://openalex.org/W3102501663","https://openalex.org/W6684072790","https://openalex.org/W6712698574","https://openalex.org/W6722226382"],"related_works":["https://openalex.org/W90906771","https://openalex.org/W2018828772","https://openalex.org/W2529185025","https://openalex.org/W2166822184","https://openalex.org/W4376639521","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280","https://openalex.org/W2117462983","https://openalex.org/W2126458834"],"abstract_inverted_index":{"Given":[0],"a":[1,11,24],"data":[2,8,12,40,97,161,240,289,295,302],"set":[3],"D":[4,30],"containing":[5],"millions":[6],"of":[7,54,131,158,252,312],"points":[9,162,241,290],"and":[10,73,110,153,224,242,298],"consumer":[13],"who":[14,306],"is":[15,83,146,220,226,247,346],"willing":[16],"to":[17,22,38,42,85,88,90,192,237,249,277],"pay":[18],"for":[19,94,107,117,148,184,323,333],"$":[20],"X":[21],"train":[23],"machine":[25],"learning":[26],"(ML)":[27],"model":[28,105],"over":[29],",":[31,120,167,187,212,297],"how":[32],"should":[33],"we":[34,49,125,189],"distribute":[35],"this":[36,47,123],"$X":[37],"each":[39],"point":[41],"reflect":[43],"its":[44],"\"value\"?":[45],"In":[46,122],"paper,":[48,124],"define":[50],"the":[51,57,80,155,256,266,363],"\"relative":[52],"value":[53,82,157,267],"data\"":[55],"via":[56],"Shapley":[58,81,92,156],"value,":[59],"as":[60,70,281],"it":[61,99],"uniquely":[62],"possesses":[63],"properties":[64],"with":[65,202],"appealing":[66],"real-world":[67],"interpretations,":[68],"such":[69,280],"fairness,":[71],"rationality":[72],"decentralizability.":[74],"For":[75],"general,":[76],"bounded":[77],"utility":[78],"functions,":[79],"known":[84],"be":[86,164],"challenging":[87],"compute:":[89],"get":[91],"values":[93],"all":[95,159],"N":[96,103,113,115,160,171,173,208,216,329,349,351],"points,":[98],"requires":[100,308],"O":[101,111,169,206,327,347],"(2":[102],")":[104,116,174,214,217,331,352,356,358],"evaluations":[106],"exact":[108,245,324],"computation":[109,305,325],"(":[112,118,139,170,185,207,210,328,348],"log":[114,172,215],"\u03f5":[119,186,211,219],"\u03b4)-approximation.":[121],"focus":[126],"on":[127,135,180,197,235],"one":[128],"popular":[129],"family":[130],"ML":[132],"models":[133],"relying":[134],"K":[136,140,150,213,225,284,330,335,355],"-nearest":[137],"neighbors":[138],"NN).":[141,336],"The":[142,260],"most":[143],"surprising":[144],"result":[145],"that":[147],"unweighted":[149],"NN":[151,285],"classifiers":[152],"regressors,":[154],"can":[163,264],"computed,":[165],"exactly":[166],"in":[168],"time":[175],"-":[176],"an":[177,194,340],"exponential":[178],"improvement":[179],"computational":[181],"complexity!":[182],"Moreover,":[183],"\u03b4)-approximation,":[188],"are":[190,291,301,320],"able":[191],"develop":[193],"algorithm":[195,246,263,276],"based":[196],"Locality":[198],"Sensitive":[199],"Hashing":[200],"(LSH)":[201],"only":[203],"sublinear":[204],"complexity":[205,332],"h":[209],"when":[218],"not":[221,227],"too":[222,228],"small":[223],"large.":[229],"We":[230,272,337],"empirically":[231],"evaluate":[232],"our":[233,244,275],"algorithms":[234],"up":[236,248],"10":[238],"million":[239],"even":[243,270],"three":[250],"orders":[251],"magnitude":[253],"faster":[254],"than":[255,362],"baseline":[257,364],"approximation":[258,262,343,365],"algorithm.":[259,366],"LSH-based":[261],"accelerate":[265],"calculation":[268],"process":[269],"further.":[271],"then":[273],"extend":[274],"other":[278],"scenarios":[279],"(1)":[282],"weighed":[283],"classifiers,":[286],"(2)":[287],"different":[288,294],"clustered":[292],"by":[293],"curators":[296],"(3)":[299],"there":[300],"analysts":[303],"providing":[304],"also":[307,316],"proper":[309],"valuation.":[310],"Some":[311],"these":[313],"extensions,":[314],"although":[315],"being":[317],"improved":[318],"exponentially,":[319],"less":[321],"practical":[322],"(e.g.,":[326],"weigthed":[334],"thus":[338],"propose":[339],"Monte":[341],"Carlo":[342],"algorithm,":[344],"which":[345],"(log":[350],"2":[353,357],"/(log":[354],"times":[359],"more":[360],"efficient":[361]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}