{"id":"https://openalex.org/W2406009284","doi":"https://doi.org/10.1137/1.9781611973440.4","title":"Selective Sampling on Probabilistic Data","display_name":"Selective Sampling on Probabilistic Data","publication_year":2014,"publication_date":"2014-04-28","ids":{"openalex":"https://openalex.org/W2406009284","doi":"https://doi.org/10.1137/1.9781611973440.4","mag":"2406009284"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611973440.4","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611973440.4","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 SIAM International Conference on 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/A5021795473","display_name":"Peng Peng","orcid":"https://orcid.org/0000-0002-7801-2285"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Peng Peng","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049858061","display_name":"Raymond Chi-Wing Wong","orcid":"https://orcid.org/0000-0001-7045-6503"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Raymond Chi-Wing Wong","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021795473"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22566158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9945999979972839,"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":0.9921000003814697,"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":0.8127949237823486},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7324000597000122},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7132797241210938},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6045886278152466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194860696792603},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5048092603683472},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49107789993286133},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47619879245758057},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34325703978538513},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.13276731967926025},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08306929469108582},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07443004846572876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8127949237823486},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7324000597000122},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7132797241210938},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6045886278152466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194860696792603},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5048092603683472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49107789993286133},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47619879245758057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34325703978538513},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.13276731967926025},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08306929469108582},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07443004846572876},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/1.9781611973440.4","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611973440.4","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 SIAM International Conference on Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-65872","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-65872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.416","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/~raywong/paper/sdm14-samplingProbLabels.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W86328269","https://openalex.org/W1484867920","https://openalex.org/W1485810016","https://openalex.org/W1502922572","https://openalex.org/W1528361845","https://openalex.org/W1542886316","https://openalex.org/W1555354714","https://openalex.org/W1564684449","https://openalex.org/W1564947197","https://openalex.org/W1600192391","https://openalex.org/W1607038179","https://openalex.org/W1827175191","https://openalex.org/W1964488740","https://openalex.org/W2009134948","https://openalex.org/W2022265986","https://openalex.org/W2043919728","https://openalex.org/W2098986246","https://openalex.org/W2113459411","https://openalex.org/W2114188922","https://openalex.org/W2114232233","https://openalex.org/W2115404432","https://openalex.org/W2123807192","https://openalex.org/W2123933185","https://openalex.org/W2126750886","https://openalex.org/W2144660879","https://openalex.org/W2148440006","https://openalex.org/W2151023586","https://openalex.org/W2157958821","https://openalex.org/W2163150561","https://openalex.org/W2167503608","https://openalex.org/W2167595980","https://openalex.org/W2185563688","https://openalex.org/W2407981807","https://openalex.org/W3120740533","https://openalex.org/W4230030242","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"In":[0,28,73],"the":[1,11,15,39,46,117,126,142],"literature":[2],"of":[3,42,48,144],"supervised":[4],"learning,":[5],"most":[6],"existing":[7],"studies":[8],"assume":[9],"that":[10,122],"labels":[12],"provided":[13],"by":[14,57],"labelers":[16,35],"are":[17],"deterministic,":[18],"which":[19,86],"may":[20,36],"introduce":[21],"noise":[22],"easily":[23],"in":[24,85,123,138],"many":[25,29,34],"real-world":[26],"applications.":[27],"applications":[30],"like":[31],"crowdsourcing,":[32],"however,":[33],"simultaneously":[37],"label":[38,47,67,127],"same":[40],"group":[41],"instances":[43],"and":[44,108],"thus":[45],"each":[49,66,87],"instance":[50,89,107],"is":[51,68,90],"associated":[52],"with":[53,70,92],"a":[54,62,71,93,98,105],"probability.":[55,72,94],"Motivated":[56],"this":[58,74],"observation,":[59],"we":[60,76,96,103,134],"propose":[61],"new":[63,106],"framework":[64],"where":[65],"enriched":[69],"paper,":[75],"study":[77],"an":[78],"interactive":[79],"sampling":[80],"strategy,":[81],"namely,":[82],"selective":[83],"sampling,":[84],"selected":[88],"labeled":[91,114],"Specifically,":[95],"flip":[97],"coin":[99],"every":[100],"time":[101],"when":[102],"read":[104],"decide":[109],"whether":[110],"it":[111],"should":[112],"be":[113,130],"according":[115],"to":[116,140],"flipping":[118],"result.":[119],"We":[120],"prove":[121],"our":[124,145],"setting":[125],"complexity":[128],"can":[129],"reduced":[131],"dramatically.":[132],"Finally,":[133],"conducted":[135],"comprehensive":[136],"experiments":[137],"order":[139],"verify":[141],"effectiveness":[143],"proposed":[146],"labeling":[147],"framework.":[148]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}