{"id":"https://openalex.org/W3154948645","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10064696","title":"Data Shapley Valuation for Efficient Batch Active Learning","display_name":"Data Shapley Valuation for Efficient Batch Active Learning","publication_year":2022,"publication_date":"2022-10-31","ids":{"openalex":"https://openalex.org/W3154948645","doi":"https://doi.org/10.1109/ieeeconf56349.2022.10064696","mag":"3154948645"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf56349.2022.10064696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10064696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"preprint","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/A5034659013","display_name":"Amirata Ghorbani","orcid":"https://orcid.org/0000-0001-6465-2321"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amirata Ghorbani","raw_affiliation_strings":["Stanford University,Department of Electrical Engineering,Stanford,CA,USA","Department of Electrical Engineering, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Zou","raw_affiliation_strings":["Stanford University,Department of Biomedical Data Science,Stanford,CA,USA","Department of Biomedical Data Science, Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Biomedical Data Science,Stanford,CA,USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Biomedical Data Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070015743","display_name":"Andre Esteva","orcid":"https://orcid.org/0000-0003-1937-9682"},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andre Esteva","raw_affiliation_strings":["Salesforce Research Salesforce,Palo Alto,CA,USA","Salesforce Research Salesforce, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Salesforce Research Salesforce,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I4210155268"]},{"raw_affiliation_string":"Salesforce Research Salesforce, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I4210155268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034659013"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.54538466,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86331545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1456","last_page":"1462"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9984999895095825,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9864000082015991,"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":0.752007007598877},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5739487409591675},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.569341778755188},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5480159521102905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296789407730103},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5234091877937317},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42857202887535095},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4146595001220703},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24973538517951965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.752007007598877},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5739487409591675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.569341778755188},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5480159521102905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296789407730103},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5234091877937317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42857202887535095},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4146595001220703},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24973538517951965}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf56349.2022.10064696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf56349.2022.10064696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","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":58,"referenced_works":["https://openalex.org/W66763315","https://openalex.org/W1562353621","https://openalex.org/W1562693942","https://openalex.org/W1580375566","https://openalex.org/W1872312298","https://openalex.org/W1912128066","https://openalex.org/W1972508834","https://openalex.org/W1978906111","https://openalex.org/W1998613841","https://openalex.org/W2098203240","https://openalex.org/W2104848109","https://openalex.org/W2117539524","https://openalex.org/W2135733005","https://openalex.org/W2139238311","https://openalex.org/W2155290553","https://openalex.org/W2343514605","https://openalex.org/W2487898712","https://openalex.org/W2581082771","https://openalex.org/W2597603852","https://openalex.org/W2774918944","https://openalex.org/W2788686132","https://openalex.org/W2895171208","https://openalex.org/W2903158431","https://openalex.org/W2910982074","https://openalex.org/W2948367246","https://openalex.org/W2949574275","https://openalex.org/W2949702430","https://openalex.org/W2949780682","https://openalex.org/W2951786554","https://openalex.org/W2962835968","https://openalex.org/W2963902936","https://openalex.org/W2970773487","https://openalex.org/W2985167557","https://openalex.org/W2990138404","https://openalex.org/W3002705197","https://openalex.org/W3008559440","https://openalex.org/W3082269314","https://openalex.org/W3118608800","https://openalex.org/W3205626500","https://openalex.org/W4234731922","https://openalex.org/W4394639701","https://openalex.org/W6637373629","https://openalex.org/W6639393196","https://openalex.org/W6639808567","https://openalex.org/W6680876916","https://openalex.org/W6682578415","https://openalex.org/W6735374517","https://openalex.org/W6735632633","https://openalex.org/W6747231328","https://openalex.org/W6748034479","https://openalex.org/W6755174528","https://openalex.org/W6758233323","https://openalex.org/W6760064560","https://openalex.org/W6762234667","https://openalex.org/W6763607942","https://openalex.org/W6764588566","https://openalex.org/W6770107572","https://openalex.org/W6774812674"],"related_works":["https://openalex.org/W2056314584","https://openalex.org/W4206195464","https://openalex.org/W1492505081","https://openalex.org/W4390062853","https://openalex.org/W2513638114","https://openalex.org/W3210156800","https://openalex.org/W1986633584","https://openalex.org/W4389256085","https://openalex.org/W2976807053","https://openalex.org/W184546935"],"abstract_inverted_index":{"Annotating":[0],"the":[1,68,82,90,93,101,110,123,147,154],"right":[2],"set":[3],"of":[4,33,70,92,96,103,125,150,156,167],"data":[5,9,35,105,127],"amongst":[6],"all":[7],"available":[8],"points":[10,36,84,106],"is":[11,23,119,143],"a":[12,24,78],"key":[13],"challenge":[14],"in":[15,30],"many":[16],"machine":[17],"learning":[18,22,44,64,73,160],"applications.":[19],"Batch":[20],"active":[21,63,72,159],"popular":[25],"approach":[26],"to":[27,109,145],"address":[28],"this,":[29],"which":[31],"batches":[32],"unlabeled":[34,87,104,126,152],"are":[37],"selected":[38],"for":[39,61],"annotation,":[40],"while":[41,169],"an":[42,86,151,164],"underlying":[43],"algorithm":[45],"gets":[46],"subsequently":[47],"updated.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"introduce":[53],"Active":[54],"Data":[55],"Shapley":[56,94],"(ADS)":[57],"\u2013a":[58],"filtering":[59],"layer":[60],"batch":[62,158],"that":[65,117,140],"significantly":[66],"increases":[67,162],"efficiency":[69,155],"existing":[71],"algorithms":[74],"by":[75,163],"pre-selecting,":[76],"using":[77],"linear":[79],"time":[80],"computation,":[81],"highest-value":[83],"from":[85],"dataset.":[88],"Using":[89],"notion":[91],"value":[95,102],"data,":[97],"our":[98],"method":[99],"estimates":[100],"with":[107],"regards":[108],"prediction":[111],"task":[112],"at":[113],"hand.":[114],"We":[115,136],"show":[116],"ADS":[118,142],"particularly":[120],"effective":[121],"when":[122,141],"pool":[124],"exhibits":[128],"real-world":[129],"caveats:":[130],"noise,":[131],"heterogeneity,":[132],"and":[133],"domain":[134],"shift.":[135],"run":[137],"experiments":[138],"demonstrating":[139],"used":[144],"pre-select":[146],"highest-ranking":[148],"portion":[149],"dataset,":[153],"state-of-the-art":[157],"methods":[161],"average":[165],"factor":[166],"6x,":[168],"preserving":[170],"performance":[171],"effectiveness.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}