{"id":"https://openalex.org/W7162555406","doi":"https://doi.org/10.48550/arxiv.2605.27043","title":"Causal Representation Learning for Generalisable Recommendation","display_name":"Causal Representation Learning for Generalisable Recommendation","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162555406","doi":"https://doi.org/10.48550/arxiv.2605.27043"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27043","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.27043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093497307","display_name":"Yorgos Felekis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felekis, Yorgos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137131624","display_name":"Michael O'Riordan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O'Riordan, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137144555","display_name":"Oriol Corcoll","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Corcoll, Oriol","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137154273","display_name":"Ciar\u00e1n M. Gilligan-Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gilligan-Lee, Ciar\u00e1n M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.24650000035762787,"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":0.24650000035762787,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07270000129938126,"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":0.0697999969124794,"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/headline","display_name":"Headline","score":0.5699999928474426},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5616000294685364},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.460999995470047},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.36629998683929443},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36480000615119934},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3450999855995178},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.3395000100135803},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.335999995470047},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.33390000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6396999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579800009727478},{"id":"https://openalex.org/C2778689934","wikidata":"https://www.wikidata.org/wiki/Q1313396","display_name":"Headline","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5414999723434448},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.460999995470047},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C23131810","wikidata":"https://www.wikidata.org/wiki/Q818574","display_name":"Observational study","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27043","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.27043","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27043","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predictive":[0],"models":[1],"trained":[2,38],"on":[3,39,108,202,218,231],"observational":[4,130],"data":[5,21,131],"often":[6],"fail":[7],"to":[8,10,181,205],"generalise":[9],"the":[11,19,26,44,56,62,82,109,113,125,145,171,176,232,246],"distributions":[12],"they":[13,36],"encounter":[14],"when":[15,18],"deployed,":[16],"especially":[17],"training":[20,57],"is":[22,138,168,194],"a":[23,33,54,69,87,118,206,238],"product":[24],"of":[25,77,112,135,142,144,160,200],"system":[27],"being":[28],"optimised.":[29],"Recommender":[30],"systems":[31],"are":[32,37],"canonical":[34],"example:":[35],"interaction":[40],"logs":[41],"confounded":[42,178],"by":[43,90],"deployed":[45],"policy,":[46],"past":[47],"user":[48],"behaviour,":[49],"and":[50,101,186,237],"platform":[51],"filtering.":[52],"As":[53],"result,":[55],"distribution":[58,64,83,155,255],"differs":[59],"substantially":[60],"from":[61,128],"candidate":[63],"scored":[65],"at":[66],"serving":[67],"time,":[68],"gap":[70],"that":[71,103,123,141,149],"makes":[72,124,170],"offline":[73,220,249],"metrics":[74],"unreliable":[75],"predictors":[76],"online":[78,224],"performance.":[79],"We":[80,95,115],"address":[81],"shift":[84],"problem":[85],"with":[86,198,241,251],"method":[88,137,172],"motivated":[89],"causal":[91,110,163,243,263],"representation":[92],"learning":[93],"(CRL).":[94],"propose":[96],"an":[97,195],"information-theoretic":[98],"disentanglement":[99,264],"criterion":[100,126],"prove":[102],"its":[104],"optimum":[105],"depends":[106],"only":[107,175],"components":[111],"input.":[114],"then":[116],"derive":[117],"tractable":[119],"variational":[120],"lower":[121],"bound":[122],"optimisable":[127],"finite":[129],"alone.":[132],"The":[133],"scope":[134],"our":[136,262],"narrower":[139,166],"than":[140],"much":[143],"CRL":[146,215],"literature,":[147],"in":[148,226],"we":[150],"target":[151,167],"better":[152,268],"generalisation":[153],"under":[154,254],"shift,":[156],"not":[157],"full":[158],"identification":[159],"all":[161,258],"latent":[162],"factors.":[164],"This":[165],"what":[169],"practical,":[173],"requiring":[174],"existing":[177],"logs,":[179],"applying":[180],"any":[182],"standard":[183],"supervised":[184],"model,":[185],"adding":[187,261],"no":[188],"inference-time":[189],"cost.":[190],"Our":[191],"headline":[192],"evaluation":[193],"A/B":[196],"test":[197],"millions":[199],"users":[201],"Spotify,":[203],"applied":[204],"production":[207],"ranker":[208],"for":[209],"personalised":[210],"playlist":[211],"generation.":[212],"A":[213],"capacity-matched":[214],"variant":[216],"performed":[217],"par":[219],"but":[221],"delivered":[222],"substantial":[223],"gains":[225,253],"listener":[227],"engagement.":[228],"Complementary":[229],"evidence":[230],"public":[233],"KuaiRand":[234],"recommendation":[235],"dataset":[236],"synthetic":[239],"benchmark":[240],"known":[242],"structure":[244],"shows":[245],"same":[247],"pattern:":[248],"parity":[250],"baseline,":[252],"shift.":[256],"Across":[257],"three":[259],"settings,":[260],"objective":[265],"yields":[266],"meaningfully":[267],"out-of-distribution":[269],"generalisation.":[270]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}