{"id":"https://openalex.org/W4367318992","doi":"https://doi.org/10.1145/3543873.3584631","title":"HAPENS: Hardness-Personalized Negative Sampling for Implicit Collaborative Filtering","display_name":"HAPENS: Hardness-Personalized Negative Sampling for Implicit Collaborative Filtering","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4367318992","doi":"https://doi.org/10.1145/3543873.3584631"},"language":"en","primary_location":{"id":"doi:10.1145/3543873.3584631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584631","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3543873.3584631","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087697792","display_name":"Haoxin Liu","orcid":"https://orcid.org/0000-0002-9614-8442"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxin Liu","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112910506","display_name":"Pu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Zhao","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027659574","display_name":"Si Qin","orcid":"https://orcid.org/0000-0002-8698-1860"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Qin","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051982930","display_name":"Yong Shi","orcid":"https://orcid.org/0000-0003-0762-8581"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Shi","raw_affiliation_strings":["Microsoft Bing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Bing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021239365","display_name":"Mirror Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mirror Xu","raw_affiliation_strings":["Microsoft Bing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Bing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088646345","display_name":"Qingwei Lin","orcid":"https://orcid.org/0000-0003-2559-2383"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Lin","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331488","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0002-9230-2799"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft Research, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5087697792"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.4582,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63943879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9804999828338623,"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/computer-science","display_name":"Computer science","score":0.6096471548080444},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.5563086867332458},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.482738196849823},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2705005407333374},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20827624201774597},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.1842447817325592},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.10368964076042175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6096471548080444},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.5563086867332458},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.482738196849823},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2705005407333374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20827624201774597},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.1842447817325592},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.10368964076042175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543873.3584631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584631","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543873.3584631","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543873.3584631","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2054141820","https://openalex.org/W2090679992","https://openalex.org/W2101409192","https://openalex.org/W2102035799","https://openalex.org/W2244405900","https://openalex.org/W2605350416","https://openalex.org/W2619206542","https://openalex.org/W2807021761","https://openalex.org/W2912500072","https://openalex.org/W2945827670","https://openalex.org/W2950491307","https://openalex.org/W2963085847","https://openalex.org/W2963642516","https://openalex.org/W3023045848","https://openalex.org/W3033630125","https://openalex.org/W3036320503","https://openalex.org/W3045200674","https://openalex.org/W3080456792","https://openalex.org/W3098468692","https://openalex.org/W3100278010","https://openalex.org/W3100848837","https://openalex.org/W3101023724","https://openalex.org/W3103801215","https://openalex.org/W3116172555","https://openalex.org/W3153687708","https://openalex.org/W3201463768","https://openalex.org/W3211143493","https://openalex.org/W4247880210"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2398165842","https://openalex.org/W197922276","https://openalex.org/W4226158052","https://openalex.org/W1809731386","https://openalex.org/W4388863299","https://openalex.org/W2160332782","https://openalex.org/W2945818642"],"abstract_inverted_index":{"For":[0],"training":[1],"implicit":[2],"collaborative":[3],"filtering":[4],"(ICF)":[5],"models,":[6],"hard":[7],"negative":[8,18,115],"sampling":[9,116,162],"(HNS)":[10],"has":[11,198],"become":[12],"a":[13,33,49,108,120,132,160],"state-of-the-art":[14],"solution":[15],"for":[16,29],"obtaining":[17],"signals":[19],"from":[20],"massive":[21,95],"uninteracted":[22],"items.":[23],"However,":[24,52],"selecting":[25],"appropriate":[26],"hardness":[27,45,56,157],"levels":[28,158],"personalized":[30,156],"recommendations":[31],"remains":[32],"fundamental,":[34],"yet":[35],"underexplored,":[36],"problem.":[37,223],"Previous":[38],"HNS":[39],"works":[40],"have":[41],"primarily":[42],"adjusted":[43],"the":[44,54,69,85,94,128,166,170,177,187,203,208,215],"level":[46,57],"by":[47],"tuning":[48],"single":[50],"hyperparameter.":[51],"applying":[53],"same":[55,171],"to":[58,64,93,202,217],"each":[59,142],"user":[60,66,74],"is":[61,89],"unsuitable":[62],"due":[63,92],"varying":[65],"behavioral":[67],"characteristics,":[68],"quantity":[70],"and":[71,76,103,110,164,182,186,194,221],"quality":[72],"of":[73,79,87,97,210],"records,":[75],"different":[77],"consistencies":[78],"models\u2019":[80],"inductive":[81],"biases.":[82],"Moreover,":[83,196],"increasing":[84],"number":[86,96],"hyperparameters":[88],"not":[90],"practical":[91,111],"users.":[98],"To":[99,207],"address":[100],"this":[101,219],"important":[102,220],"challenging":[104,222],"problem,":[105],"we":[106,213],"propose":[107],"model-agnostic":[109],"approach":[112],"called":[113],"hardness-personalized":[114],"(HAPENS).":[117],"HAPENS":[118,175,197],"uses":[119],"two-stage":[121],"approach:":[122],"in":[123],"stage":[124,148],"one,":[125],"it":[126,150],"trains":[127,165],"ICF":[129],"model":[130,168],"with":[131,159,169],"customized":[133],"objective":[134],"function":[135],"that":[136],"optimizes":[137],"its":[138,192],"worst":[139,153],"performance":[140],"on":[141,176],"user\u2019s":[143],"interacted":[144],"item":[145],"set.":[146],"In":[147],"two,":[149],"utilizes":[151],"these":[152],"performances":[154],"as":[155],"well-designed":[161],"distribution,":[163],"final":[167],"architecture.":[172],"We":[173],"evaluated":[174],"collected":[178],"Bing":[179,204],"advertising":[180,205],"dataset":[181],"one":[183],"public":[184],"dataset,":[185],"comprehensive":[188],"experimental":[189],"results":[190],"demonstrate":[191],"robustness":[193],"superiority.":[195],"delivered":[199],"significant":[200],"benefits":[201],"system.":[206],"best":[209],"our":[211],"knowledge,":[212],"are":[214],"first":[216],"study":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}