{"id":"https://openalex.org/W4416252273","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228603","title":"A Theoretical Analysis of Recommendation Loss Functions under Negative Sampling","display_name":"A Theoretical Analysis of Recommendation Loss Functions under Negative Sampling","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252273","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228603"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074443891","display_name":"Giulia Di Teodoro","orcid":"https://orcid.org/0000-0002-0418-0067"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giulia Di Teodoro","raw_affiliation_strings":["University of Pisa,Information Engineering Department,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa,Information Engineering Department,Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074346581","display_name":"Federico Siciliano","orcid":"https://orcid.org/0000-0003-1339-6983"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federico Siciliano","raw_affiliation_strings":["Sapienza University of Rome,Department of Computer, Control and Management Engineering,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Department of Computer, Control and Management Engineering,Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa,Information Engineering Department,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa,Information Engineering Department,Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044165871","display_name":"Fabrizio Silvestri","orcid":"https://orcid.org/0000-0001-7669-9055"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Silvestri","raw_affiliation_strings":["Sapienza University of Rome,Department of Computer, Control and Management Engineering,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Department of Computer, Control and Management Engineering,Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.44231961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.8978000283241272,"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":0.8978000283241272,"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":0.009100000374019146,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.007400000002235174,"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/categorical-variable","display_name":"Categorical variable","score":0.6917999982833862},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5722000002861023},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.545799970626831},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5364999771118164},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5235999822616577},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4569000005722046},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.453900009393692},{"id":"https://openalex.org/keywords/mean-reciprocal-rank","display_name":"Mean reciprocal rank","score":0.45010000467300415},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.423799991607666}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5722000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645999908447266},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5364999771118164},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C44083865","wikidata":"https://www.wikidata.org/wiki/Q3853443","display_name":"Mean reciprocal rank","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39239999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C136979486","wikidata":"https://www.wikidata.org/wiki/Q773483","display_name":"Existential quantification","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C29143872","wikidata":"https://www.wikidata.org/wiki/Q876690","display_name":"Business process reengineering","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1343931","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1343931","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1976999215","https://openalex.org/W2027731328","https://openalex.org/W2069870183","https://openalex.org/W2071702404","https://openalex.org/W2102035799","https://openalex.org/W2140310134","https://openalex.org/W2157665330","https://openalex.org/W2219888463","https://openalex.org/W2539247542","https://openalex.org/W2605350416","https://openalex.org/W2783272285","https://openalex.org/W2891899765","https://openalex.org/W2959353218","https://openalex.org/W2963367478","https://openalex.org/W2984100107","https://openalex.org/W3012952868","https://openalex.org/W3045200674","https://openalex.org/W3121535423","https://openalex.org/W3185773347","https://openalex.org/W4224315924","https://openalex.org/W4283205337","https://openalex.org/W4296604471","https://openalex.org/W4319653823","https://openalex.org/W4385270446","https://openalex.org/W4385825460","https://openalex.org/W4385849288","https://openalex.org/W4386729798","https://openalex.org/W4389675217","https://openalex.org/W4405754319"],"related_works":[],"abstract_inverted_index":{"Loss":[0],"functions":[1],"like":[2,76],"Categorical":[3],"Cross":[4,8],"Entropy":[5,9],"(CCE),":[6],"Binary":[7],"(BCE),":[10],"and":[11,35,47,82,90,120,131,176,186],"Bayesian":[12],"Personalized":[13],"Ranking":[14],"(BPR)":[15],"are":[16,122,189],"commonly":[17],"used":[18],"in":[19,155],"training":[20],"Recommender":[21],"Systems":[22],"(RSs)":[23],"to":[24,136],"differentiate":[25],"positive":[26],"items":[27,99],"-":[28,34],"those":[29],"interacted":[30],"with":[31],"by":[32,64,88],"users":[33],"negative":[36,55,98,110,114,127],"items.":[37],"While":[38],"prior":[39],"works":[40],"empirically":[41,179],"showed":[42],"that":[43,66,118,144,163],"CCE":[44,67,121],"outperforms":[45],"BCE":[46,164],"BPR":[48,89,119],"when":[49,124],"using":[50,93],"the":[51,69,94,107,137,145,166],"full":[52,95],"set":[53,96],"of":[54,97,109],"items,":[56],"we":[57,116],"provide":[58],"a":[59,125,156],"theoretical":[60,182],"explanation":[61],"for":[62,103,151],"this":[63],"proving":[65],"offers":[68,165],"tightest":[70],"lower":[71,149],"bound":[72,168],"on":[73,169,173],"ranking":[74],"metrics":[75],"Normalized":[77],"Discounted":[78],"Cumulative":[79],"Gain":[80],"(NDCG)":[81],"Mean":[83],"Reciprocal":[84],"Rank":[85],"(MRR),":[86,153],"followed":[87],"BCE.":[91],"However,":[92],"is":[100,129],"computationally":[101],"infeasible":[102],"large-scale":[104],"RSs,":[105],"prompting":[106],"use":[108],"sampling":[111],"techniques.":[112],"Under":[113],"sampling,":[115],"reveal":[117],"equivalent":[123],"single":[126],"sample":[128],"drawn,":[130],"all":[132],"three":[133],"losses":[134,147],"converge":[135],"same":[138],"global":[139],"minimum.":[140],"We":[141],"further":[142],"demonstrate":[143],"sampled":[146],"remain":[148],"bounds":[150],"NDCG":[152,170],"albeit":[154],"probabilistic":[157],"sense.":[158],"Our":[159,184],"worst-case":[160],"analysis":[161],"shows":[162],"strongest":[167],"(MRR).":[171],"Experiments":[172],"five":[174],"datasets":[175],"four":[177],"models":[178],"support":[180],"these":[181],"findings.":[183],"code":[185],"supplementary":[187],"material":[188],"available":[190],"at":[191],"https://github.com/federicosiciliano/recsys_losses.git.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-14T00:00:00"}