{"id":"https://openalex.org/W4403578188","doi":"https://doi.org/10.1145/3627673.3679763","title":"Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits","display_name":"Mitigating Exposure Bias in Online Learning to Rank Recommendation: A Novel Reward Model for Cascading Bandits","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403578188","doi":"https://doi.org/10.1145/3627673.3679763"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679763","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009118126","display_name":"Masoud Mansoury","orcid":"https://orcid.org/0000-0002-9938-0212"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Masoud Mansoury","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082580430","display_name":"Bamshad Mobasher","orcid":"https://orcid.org/0000-0001-9701-9178"},"institutions":[{"id":"https://openalex.org/I118353179","display_name":"DePaul University","ror":"https://ror.org/04xtx5t16","country_code":"US","type":"education","lineage":["https://openalex.org/I118353179"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bamshad Mobasher","raw_affiliation_strings":["DePaul University, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"DePaul University, Chicago, USA","institution_ids":["https://openalex.org/I118353179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057277609","display_name":"Herke van Hoof","orcid":"https://orcid.org/0000-0002-1583-3692"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Herke van Hoof","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009118126"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":2.53,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90123007,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1638","last_page":"1648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9945999979972839,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.7275633811950684},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.5075258016586304},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.498091459274292},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.482862263917923},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.47406357526779175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43603262305259705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4322882890701294},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.14423701167106628},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12040981650352478},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10833874344825745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275633811950684},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.5075258016586304},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.498091459274292},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.482862263917923},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.47406357526779175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43603262305259705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4322882890701294},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.14423701167106628},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12040981650352478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10833874344825745},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3627673.3679763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679763","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/a9b3cd8e-f3fa-452c-ac7f-fa87de187fa8","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/mitigating-exposure-bias-in-online-learning-to-rank-recommendation(a9b3cd8e-f3fa-452c-ac7f-fa87de187fa8).html","pdf_url":"https://pure.uva.nl/ws/files/238155799/Mitigating_Exposure_Bias_in_Online_Learning_to_Rank_Recommendation.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mansoury, M, Mobasher, B & van Hoof, H 2024, Mitigating Exposure Bias in Online Learning to Rank Recommendation : A Novel Reward Model for Cascading Bandits. in CIKM '24 : Proceedings of the 33rd ACM International Conference on Information and Knowledge Management : October, 21-25. 2024, Boise, ID, USA. Association for Computing Machinery, New York, NY, pp. 1638-1648, 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, United States, 21/10/24. https://doi.org/10.1145/3627673.3679763","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/a9b3cd8e-f3fa-452c-ac7f-fa87de187fa8","is_oa":true,"landing_page_url":"https://hdl.handle.net/11245.1/a9b3cd8e-f3fa-452c-ac7f-fa87de187fa8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mansoury, M, Mobasher, B & van Hoof, H 2024, Mitigating Exposure Bias in Online Learning to Rank Recommendation : A Novel Reward Model for Cascading Bandits. in CIKM '24 : Proceedings of the 33rd ACM International Conference on Information and Knowledge Management : October, 21-25. 2024, Boise, ID, USA. Association for Computing Machinery, New York, NY, pp. 1638-1648, 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, United States, 21/10/24. https://doi.org/10.1145/3627673.3679763","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679763","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679763","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1968927634","https://openalex.org/W1971040550","https://openalex.org/W1992549066","https://openalex.org/W2039522160","https://openalex.org/W2086456706","https://openalex.org/W2135981994","https://openalex.org/W2148398661","https://openalex.org/W2155106456","https://openalex.org/W2258625391","https://openalex.org/W2401983063","https://openalex.org/W2559655401","https://openalex.org/W2611179066","https://openalex.org/W2744446984","https://openalex.org/W2750237488","https://openalex.org/W2787991113","https://openalex.org/W2793816798","https://openalex.org/W2893370267","https://openalex.org/W2897955056","https://openalex.org/W2950344037","https://openalex.org/W3012903288","https://openalex.org/W3048919590","https://openalex.org/W3092103025","https://openalex.org/W3094546485","https://openalex.org/W3098894878","https://openalex.org/W3102518922","https://openalex.org/W3168126546","https://openalex.org/W3201310492","https://openalex.org/W4281848017","https://openalex.org/W4284690424","https://openalex.org/W4361271424","https://openalex.org/W4376123208","https://openalex.org/W4386876121","https://openalex.org/W4396821616"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2772359885","https://openalex.org/W3011471740","https://openalex.org/W2954428433","https://openalex.org/W2884580467","https://openalex.org/W2572315477","https://openalex.org/W2138935942","https://openalex.org/W3003205888","https://openalex.org/W2758702176"],"abstract_inverted_index":{"Exposure":[0],"bias":[1,22,94,118,140,187],"is":[2],"a":[3,29,40,96,121,241],"well-known":[4,99],"issue":[5,54],"in":[6,17,35,55,95,112,126,141,178,200],"recommender":[7],"systems":[8],"where":[9,78],"items":[10,31,125,195],"and":[11,119,171],"suppliers":[12],"are":[13,32,81],"not":[14],"equally":[15],"represented":[16],"the":[18,127,142,146,160,173,176,179,190,194,201,217,221,229,235],"recommendation":[19,36,59,68,79,128,180,202,230],"results.":[20,129],"This":[21],"becomes":[23],"particularly":[24],"problematic":[25],"over":[26,225],"time":[27,226],"as":[28,71,104],"few":[30],"repeatedly":[33],"over-represented":[34],"lists,":[37],"leading":[38],"to":[39,66,115,137,193],"feedback":[41,170],"loop":[42],"that":[43,133,158,211],"further":[44],"amplifies":[45],"this":[46,53,89],"bias.":[47],"Although":[48],"extensive":[49],"research":[50],"has":[51,63],"addressed":[52],"model-based":[56],"or":[57],"neighborhood-based":[58],"algorithms,":[60],"less":[61],"attention":[62],"been":[64],"paid":[65],"online":[67],"models,":[69],"such":[70],"those":[72],"based":[73,163,196],"on":[74,164,197],"top-K":[75],"contextual":[76,100],"bandits,":[77],"models":[80],"dynamically":[82],"updated":[83],"with":[84,206],"ongoing":[85,149],"user":[86,150,169],"feedback.":[87],"In":[88],"paper,":[90],"we":[91,239],"study":[92],"exposure":[93,117,139,186,199,218],"class":[97],"of":[98,124,148,175,220],"bandit":[101],"algorithms":[102,111,135],"known":[103],"Linear":[105],"Cascading":[106],"Bandits,.":[107],"We":[108,152],"analyze":[109],"these":[110,134],"their":[113,198],"ability":[114],"handle":[116],"provide":[120],"fair":[122],"representation":[123],"Our":[130,204],"analysis":[131],"reveals":[132],"fail":[136],"mitigate":[138],"long":[143],"run":[144],"during":[145],"course":[147],"interactions.":[151],"propose":[153],"an":[154],"Exposure-Aware":[155],"reward":[156,214],"model":[157,161,184,215],"updates":[159],"parameters":[162],"two":[165,207],"factors:":[166],"1)":[167],"implicit":[168],"2)":[172],"position":[174],"item":[177],"list.":[181,203],"The":[182],"proposed":[183,213,249],"mitigates":[185],"by":[188],"controlling":[189],"utility":[191],"assigned":[192],"experiments":[205],"real-world":[208],"datasets":[209],"show":[210],"our":[212,248],"improves":[216],"fairness":[219],"linear":[222],"cascading":[223],"bandits":[224],"while":[227],"maintaining":[228],"accuracy.":[231],"It":[232],"also":[233],"outperforms":[234],"current":[236],"baselines.":[237],"Finally,":[238],"prove":[240],"high":[242],"probability":[243],"upper":[244],"regret":[245],"bound":[246],"for":[247,254],"model,":[250],"providing":[251],"theoretical":[252],"guarantees":[253],"its":[255],"performance.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}