{"id":"https://openalex.org/W7134810663","doi":"https://doi.org/10.48550/arxiv.2603.06589","title":"Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing","display_name":"Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7134810663","doi":"https://doi.org/10.48550/arxiv.2603.06589"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06589","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102029996","display_name":"Hailing Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Hailing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128643252","display_name":"Yafang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yafang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047994911","display_name":"Hemeng Tao","orcid":"https://orcid.org/0000-0002-3763-2269"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Hemeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123170897","display_name":"Fengyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fengyu","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17595443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.515999972820282,"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":0.515999972820282,"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":0.16699999570846558,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0560000017285347,"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/debiasing","display_name":"Debiasing","score":0.79339998960495},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5180000066757202},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5009999871253967},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4025000035762787},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.40149998664855957},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.40119999647140503},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.79339998960495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5292999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286999940872192},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.40149998664855957},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C17418463","wikidata":"https://www.wikidata.org/wiki/Q3455874","display_name":"Isotonic regression","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06589","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.06589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06589","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.06589","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":{"Model":[0],"calibration":[1,25,66,87,111,164,182],"and":[2,30,63,88,141,184],"debiasing":[3,89],"are":[4],"fundamental":[5],"yet":[6],"operationally":[7],"expensive":[8],"challenges":[9],"in":[10,97,119,179],"large-scale":[11],"recommendation":[12],"systems.":[13],"Existing":[14],"approaches":[15],"treat":[16],"them":[17],"as":[18,78],"separate":[19,65],"problems":[20,47],"requiring":[21,55],"distinct":[22],"infrastructure:":[23],"post-hoc":[24,137],"pipelines,":[26],"propensity":[27,61],"estimation":[28],"workflows,":[29],"per-segment":[31],"model":[32,83],"farms.":[33],"We":[34],"introduce":[35],"the":[36,82],"Isotonic":[37],"Layer,":[38],"a":[39,49,98,129,153,157,167],"differentiable":[40],"piecewise":[41],"linear":[42],"module":[43],"that":[44,114,160],"unifies":[45],"both":[46],"within":[48,146],"single,":[50],"lightweight":[51],"architectural":[52],"component":[53],"-":[54],"no":[56,60,64,125],"additional":[57],"data":[58],"preprocessing,":[59],"estimation,":[62],"pipelines.":[67],"The":[68,133],"core":[69],"insight":[70],"is":[71],"elegant:":[72],"by":[73],"parameterizing":[74],"non-negative":[75],"bucket":[76],"weights":[77],"learnable":[79],"context":[80],"embeddings,":[81],"automatically":[84],"learns":[85],"all":[86],"functions":[90],"end-to-end":[91,169],"from":[92],"standard":[93],"training":[94],"data.":[95],"Swapping":[96],"different":[99],"embedding":[100,131],"(position,":[101],"device":[102],"type,":[103],"advertiser":[104],"ID,":[105],"or":[106],"any":[107,120],"combination)":[108],"instantly":[109],"yields":[110],"tailored":[112],"to":[113],"sub-segment":[115],"at":[116],"arbitrary":[117],"granularity":[118],"high-dimensional":[121],"feature":[122],"space,":[123],"with":[124,166],"engineering":[126],"changes":[127],"beyond":[128],"single":[130,168],"lookup.":[132],"same":[134],"layer":[135],"handles":[136],"calibration,":[138],"position":[139],"debiasing,":[140],"heterogeneous":[142],"multi-task":[143],"bias":[144],"correction":[145],"one":[147],"unified":[148],"framework.":[149],"This":[150],"paper":[151],"offers":[152],"principled,":[154],"practical":[155],"simplification:":[156],"plug-and-play":[158],"solution":[159],"replaces":[161],"fragmented,":[162],"high-maintenance":[163],"infrastructure":[165],"trainable":[170],"component.":[171],"Extensive":[172],"production":[173],"A/B":[174],"tests":[175],"confirm":[176],"significant":[177],"improvements":[178],"predictive":[180],"accuracy,":[181],"fidelity,":[183],"ranking":[185],"consistency.":[186]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-11T00:00:00"}