{"id":"https://openalex.org/W4385849288","doi":"https://doi.org/10.1145/3604915.3608783","title":"gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling","display_name":"gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling","publication_year":2023,"publication_date":"2023-09-14","ids":{"openalex":"https://openalex.org/W4385849288","doi":"https://doi.org/10.1145/3604915.3608783"},"language":"en","primary_location":{"id":"doi:10.1145/3604915.3608783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.07192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100748224","display_name":"Aleksandr V. Petrov","orcid":"https://orcid.org/0000-0002-0911-3605"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aleksandr Vladimirovich Petrov","raw_affiliation_strings":["School of Computing Science, University of Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0911-3605","affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057643560","display_name":"Craig Macdonald","orcid":"https://orcid.org/0000-0003-3143-279X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Craig Macdonald","raw_affiliation_strings":["University of Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-3143-279X","affiliations":[{"raw_affiliation_string":"University of Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100748224"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":17.8659,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.99223936,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9857000112533569,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9703999757766724,"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/movielens","display_name":"MovieLens","score":0.9437736868858337},{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.9385093450546265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6643259525299072},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6027354001998901},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5289473533630371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48917415738105774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48337453603744507},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.43541547656059265},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.42941442131996155},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41191181540489197},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3716632127761841},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3658143877983093},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.361980140209198},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.2573370933532715},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.24249368906021118},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23973065614700317},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16571184992790222},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10680478811264038}],"concepts":[{"id":"https://openalex.org/C2776156558","wikidata":"https://www.wikidata.org/wiki/Q4353746","display_name":"MovieLens","level":4,"score":0.9437736868858337},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.9385093450546265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643259525299072},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6027354001998901},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5289473533630371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48917415738105774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48337453603744507},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.43541547656059265},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.42941442131996155},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41191181540489197},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3716632127761841},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3658143877983093},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.361980140209198},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.2573370933532715},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.24249368906021118},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23973065614700317},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16571184992790222},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10680478811264038},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3604915.3608783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604915.3608783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.07192","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.07192","pdf_url":"https://arxiv.org/pdf/2308.07192","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.gla.ac.uk:301348","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/62761.html>","pdf_url":"https://eprints.gla.ac.uk/301348/3/301348.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.07192","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.07192","pdf_url":"https://arxiv.org/pdf/2308.07192","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385849288.pdf","grobid_xml":"https://content.openalex.org/works/W4385849288.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1517590677","https://openalex.org/W1976999215","https://openalex.org/W2100664567","https://openalex.org/W2110953678","https://openalex.org/W2114123573","https://openalex.org/W2171279286","https://openalex.org/W2539247542","https://openalex.org/W2741544350","https://openalex.org/W2783272285","https://openalex.org/W2902040508","https://openalex.org/W2963367478","https://openalex.org/W2984100107","https://openalex.org/W3032861513","https://openalex.org/W3065542300","https://openalex.org/W3089147479","https://openalex.org/W3100260481","https://openalex.org/W3102755086","https://openalex.org/W3121535423","https://openalex.org/W3133849783","https://openalex.org/W3185773347","https://openalex.org/W3201149665","https://openalex.org/W3206127589","https://openalex.org/W3213241618","https://openalex.org/W4296591831","https://openalex.org/W4296604471","https://openalex.org/W4296604567","https://openalex.org/W4306317705","https://openalex.org/W4308517729","https://openalex.org/W4385595407"],"related_works":["https://openalex.org/W2398491113","https://openalex.org/W4400199659","https://openalex.org/W4384919653","https://openalex.org/W2794657157","https://openalex.org/W4253467046","https://openalex.org/W4251085376","https://openalex.org/W2066240519","https://openalex.org/W2775388773","https://openalex.org/W2964083560","https://openalex.org/W3117807895"],"abstract_inverted_index":{"A":[0],"large":[1,15,237],"catalogue":[2],"size":[3],"is":[4,126,138,234],"one":[5],"of":[6,17,46,65,78,88,181],"the":[7,44,50,63,75,79,86,100,116,129,134,141,169,184,200,214],"central":[8],"challenges":[9],"in":[10,49,99,104,136,229],"training":[11,51,220,224],"recommendation":[12],"models:":[13],"a":[14,69,150,204],"number":[16,180],"items":[18,30],"makes":[19],"them":[20],"memory":[21],"and":[22,53,158,183],"computationally":[23],"inefficient":[24],"to":[25,36,61,95,123,128,140,231],"compute":[26],"scores":[27],"for":[28,85,236],"all":[29],"during":[31],"training,":[32],"forcing":[33],"these":[34],"models":[35,55,92],"deploy":[37],"negative":[38,41,58],"sampling.":[39],"However,":[40],"sampling":[42,59],"increases":[43],"proportion":[45],"positive":[47,66],"interactions":[48,67],"data,":[52],"therefore":[54],"trained":[56],"with":[57],"tend":[60],"overestimate":[62],"probabilities":[64],"\u2013":[68],"phenomenon":[70],"we":[71,110,148],"call":[72],"overconfidence.":[73,165],"While":[74],"absolute":[76],"values":[77],"predicted":[80],"scores/probabilities":[81],"are":[82],"not":[83,198],"important":[84],"ranking":[87],"retrieved":[89],"recommendations,":[90],"overconfident":[91],"may":[93],"fail":[94],"estimate":[96],"nuanced":[97],"differences":[98],"top-ranked":[101],"items,":[102],"resulting":[103],"degraded":[105],"performance.":[106],"In":[107],"this":[108],"paper,":[109],"show":[111,188],"that":[112,133,161,176,195,239],"overconfidence":[113,201],"explains":[114],"why":[115],"popular":[117],"SASRec":[118,175],"model":[119],"underperforms":[120],"when":[121],"compared":[122],"BERT4Rec.":[124],"This":[125],"contrary":[127],"BERT4Rec":[130,209],"authors\u2019":[131],"explanation":[132],"difference":[135],"performance":[137],"due":[139],"bi-directional":[142],"attention":[143],"mechanism.":[144],"To":[145],"mitigate":[146,164],"overconfidence,":[147],"propose":[149,168],"novel":[151],"Generalised":[152],"Binary":[153],"Cross-Entropy":[154],"Loss":[155],"function":[156],"(gBCE)":[157],"theoretically":[159],"prove":[160],"it":[162],"can":[163,207],"We":[166,187],"further":[167],"gSASRec":[170,196,206,233],"model,":[171],"an":[172,178],"improvement":[173],"over":[174],"deploys":[177],"increased":[179],"negatives":[182],"gBCE":[185],"loss.":[186],"through":[189],"detailed":[190],"experiments":[191],"on":[192,213,226],"three":[193],"datasets":[194,238],"does":[197],"exhibit":[199],"problem.":[202],"As":[203],"result,":[205],"outperform":[208],"(e.g.":[210,222],"+9.47%":[211],"NDCG":[212],"MovieLens-1M":[215],"dataset),":[216],"while":[217],"requiring":[218],"less":[219],"time":[221,225],"-73%":[223],"MovieLens-1M).":[227],"Moreover,":[228],"contrast":[230],"BERT4Rec,":[232],"suitable":[235],"contain":[240],"more":[241],"than":[242],"1":[243],"million":[244],"items.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":17}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-10-10T00:00:00"}