{"id":"https://openalex.org/W7162800639","doi":"https://doi.org/10.1145/3770854.3780320","title":"Offline behavioral data selection","display_name":"Offline behavioral data selection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7162800639","doi":"https://doi.org/10.1145/3770854.3780320"},"language":"en","primary_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/215435","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/215435","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"},"type":"conference-paper","indexed_in":[],"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/A5036865546","display_name":"Shiye Lei","orcid":"https://orcid.org/0000-0001-7810-9346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Shiye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137318642","display_name":"Zhihao Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137360569","display_name":"Dacheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Dacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.37380000948905945,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.37380000948905945,"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":0.1023000031709671,"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":0.07680000364780426,"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/ranking","display_name":"Ranking (information retrieval)","score":0.5360000133514404},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49059998989105225},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.48190000653266907},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46970000863075256},{"id":"https://openalex.org/keywords/behavioral-modeling","display_name":"Behavioral modeling","score":0.45730000734329224},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.39910000562667847},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6723999977111816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6394000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6079999804496765},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C83804111","wikidata":"https://www.wikidata.org/wiki/Q1063558","display_name":"Behavioral pattern","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dr.ntu.edu.sg:10356/215435","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/215435","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5755072832107544,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Behavioral":[0],"cloning":[1],"is":[2,108,158],"a":[3,53,86,97],"widely":[4],"adopted":[5],"approach":[6],"for":[7,76,152],"offline":[8,19,43,104,153],"policy":[9,46,68],"learning":[10],"from":[11,102],"expert":[12],"demonstrations.":[13],"However,":[14],"the":[15,38,57,64],"large":[16],"scale":[17],"of":[18,56],"behavioral":[20,44,105,154],"datasets":[21],"often":[22],"results":[23],"in":[24,30,42],"computationally":[25],"intensive":[26],"training":[27],"when":[28,50],"used":[29],"downstream":[31],"tasks.":[32],"In":[33],"this":[34,61,82],"paper,":[35],"we":[36,84],"uncover":[37],"striking":[39],"data":[40,79,150],"saturation":[41],"data:":[45],"performance":[47,69],"rapidly":[48],"saturates":[49],"trained":[51],"on":[52,110,142],"small":[54],"fraction":[55],"dataset.":[58],"We":[59],"attribute":[60],"effect":[62],"to":[63],"weak":[65],"alignment":[66],"between":[67],"and":[70,121,133,139],"test":[71],"loss,":[72],"revealing":[73],"substantial":[74],"room":[75],"improvement":[77],"through":[78],"selection.":[80],"To":[81],"end,":[83],"propose":[85],"simple":[87],"yet":[88,99],"effective":[89],"method,":[90],"Stepwise":[91],"Dual":[92],"Ranking":[93],"(SDR),":[94],"which":[95,117,125],"extracts":[96],"compact":[98],"informative":[100],"subset":[101],"large-scale":[103],"datasets.":[106],"SDR":[107,147],"build":[109],"two":[111],"key":[112],"principles:":[113],"(1)":[114],"stepwise":[115],"clip,":[116],"prioritizes":[118],"early-stage":[119],"data;":[120],"(2)":[122],"dual":[123],"ranking,":[124],"selects":[126],"samples":[127],"with":[128],"both":[129],"high":[130],"action-value":[131],"rank":[132],"low":[134],"state-density":[135],"rank.":[136],"Extensive":[137],"experiments":[138],"ablation":[140],"studies":[141],"D4RL":[143],"benchmarks":[144],"demonstrate":[145],"that":[146],"significantly":[148],"enhances":[149],"selection":[151],"data.":[155],"The":[156],"code":[157],"available":[159],"at":[160],"https://github.com/LeavesLei/stepwise_dual_ranking.":[161]},"counts_by_year":[],"updated_date":"2026-07-02T06:12:58.138171","created_date":"2026-05-30T00:00:00"}