{"id":"https://openalex.org/W7161710335","doi":"https://doi.org/10.48550/arxiv.2605.17863","title":"DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems","display_name":"DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7161710335","doi":"https://doi.org/10.48550/arxiv.2605.17863"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136481041","display_name":"Yiqing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yiqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102440122","display_name":"Xinlong Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136463698","display_name":"Zhao Liu","orcid":"https://orcid.org/0000-0003-1734-1824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136486013","display_name":"Xiao Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136466730","display_name":"Ruiming Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ruiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136503125","display_name":"Han Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136471020","display_name":"Kun Gai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gai, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.7034000158309937,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.7034000158309937,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05689999833703041,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04280000180006027,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.9775000214576721},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.8259999752044678},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6287999749183655},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5507000088691711},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.5490999817848206},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5127999782562256},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.49900001287460327},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4440000057220459},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.42590001225471497}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9775000214576721},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8259999752044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652999758720398},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4440000057220459},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.32510000467300415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Watch-time":[0],"prediction":[1,128],"is":[2,219],"a":[3,27,69,79,97,106,122,141,165,180,207],"central":[4],"regression":[5],"task":[6],"in":[7,47,185,191],"short-video":[8,138],"recommender":[9],"systems,":[10],"where":[11],"labels":[12],"are":[13],"highly":[14],"long-tailed":[15,103,213],"and":[16,38,121,140,152,157,178,205],"residual":[17,61,86,112],"errors":[18,44],"vary":[19],"systematically":[20],"across":[21,155],"observed":[22],"watch-time":[23,55,74],"regions.":[24],"In":[25,159],"practice,":[26],"model":[28],"may":[29],"appear":[30],"globally":[31],"calibrated":[32],"while":[33],"still":[34],"overestimating":[35],"short":[36],"views":[37],"underestimating":[39],"long":[40],"views,":[41],"because":[42],"opposite":[43],"cancel":[45],"out":[46],"aggregate.":[48],"Existing":[49],"methods":[50],"mainly":[51],"improve":[52],"the":[53,160,171],"first-stage":[54],"predictor,":[56,81],"but":[57],"often":[58],"leave":[59],"such":[60],"distributional":[62],"bias":[63,204],"insufficiently":[64],"corrected.":[65],"We":[66,133],"propose":[67],"DADF,":[68],"distribution-aware":[70,99],"debiasing":[71,212],"framework":[72],"for":[73,101,109,211],"regression.":[75],"Instead":[76],"of":[77,90],"replacing":[78],"deployed":[80],"DADF":[82,92,135,146,199],"performs":[83],"second-stage":[84],"multiplicative":[85],"correction":[87,104],"on":[88,136],"top":[89],"it.":[91],"combines":[93],"three":[94],"complementary":[95],"designs:":[96],"dynamic":[98],"transformation":[100],"stabilizing":[102],"targets,":[105],"debias-factor-aware":[107],"module":[108,124],"modeling":[110],"heterogeneous":[111],"patterns":[113],"using":[114],"inference-time":[115],"observable":[116],"factors,":[117],"especially":[118],"video":[119],"duration,":[120],"multi-label-aware":[123],"that":[125,198],"exploits":[126],"auxiliary":[127],"signals":[129],"from":[130],"engagement":[131],"heads.":[132],"evaluate":[134],"public":[137],"benchmarks":[139],"large-scale":[142],"industrial":[143,161],"ranking":[144,153],"system.":[145],"consistently":[147],"improves":[148],"both":[149],"pointwise":[150],"accuracy":[151],"quality":[154],"datasets":[156],"backbones.":[158],"setting,":[162],"it":[163],"achieves":[164],"1.88":[166],"percentage-point":[167],"WUAUC":[168],"gain":[169],"over":[170],"production":[172],"baseline,":[173],"reduces":[174],"MAE":[175],"by":[176],"12.57%,":[177],"yields":[179],"statistically":[181],"significant":[182],"0.347%":[183],"lift":[184],"average":[186],"time":[187],"spent":[188],"per":[189],"device":[190],"online":[192],"A/B":[193],"testing.":[194],"These":[195],"results":[196],"demonstrate":[197],"effectively":[200],"mitigates":[201],"local":[202],"calibration":[203],"provides":[206],"practical":[208],"plug-in":[209],"solution":[210],"continuous":[214],"targets.":[215],"The":[216],"source":[217],"code":[218],"available":[220],"at":[221],"https://github.com/liuzhao09/DADF.":[222]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}