{"id":"https://openalex.org/W4212898959","doi":"https://doi.org/10.1145/3488560.3498439","title":"On Sampling Collaborative Filtering Datasets","display_name":"On Sampling Collaborative Filtering Datasets","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4212898959","doi":"https://doi.org/10.1145/3488560.3498439"},"language":"en","primary_location":{"id":"doi:10.1145/3488560.3498439","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3488560.3498439","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3488560.3498439","source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3488560.3498439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005200778","display_name":"Noveen Sachdeva","orcid":"https://orcid.org/0000-0003-1228-746X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Noveen Sachdeva","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028220093","display_name":"Carole-Jean Wu","orcid":"https://orcid.org/0000-0002-9032-7239"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carole-Jean Wu","raw_affiliation_strings":["Facebook AI Research, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005200778"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.6082,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85385385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"842","last_page":"850"},"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":0.998199999332428,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9976000189781189,"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":0.8461596965789795},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.8335126638412476},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7612066268920898},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.7161131501197815},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6459700465202332},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6287850141525269},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.619138240814209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4764975905418396},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4717876613140106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3789556622505188},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.15394511818885803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0746544897556305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461596965789795},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8335126638412476},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7612066268920898},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.7161131501197815},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6459700465202332},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6287850141525269},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.619138240814209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4764975905418396},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4717876613140106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3789556622505188},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.15394511818885803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0746544897556305},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3488560.3498439","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3488560.3498439","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3488560.3498439","source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.04768","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.04768","pdf_url":"https://arxiv.org/pdf/2201.04768","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3488560.3498439","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3488560.3498439","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3488560.3498439","source":{"id":"https://openalex.org/S4363608885","display_name":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Fifteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G5055296519","display_name":null,"funder_award_id":"1750063","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4212898959.pdf","grobid_xml":"https://content.openalex.org/works/W4212898959.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2001259128","https://openalex.org/W2040615703","https://openalex.org/W2108598243","https://openalex.org/W2111275322","https://openalex.org/W2146008005","https://openalex.org/W2419501139","https://openalex.org/W2605350416","https://openalex.org/W2640408555","https://openalex.org/W2788919350","https://openalex.org/W2901227482","https://openalex.org/W2914584698","https://openalex.org/W2963085847","https://openalex.org/W2963809228","https://openalex.org/W2971196067","https://openalex.org/W2990138404","https://openalex.org/W3001218531","https://openalex.org/W3026230850","https://openalex.org/W3081170586","https://openalex.org/W3088231796","https://openalex.org/W3099117208","https://openalex.org/W3101887415","https://openalex.org/W4297794619","https://openalex.org/W4376548770"],"related_works":["https://openalex.org/W2772628444","https://openalex.org/W1484355083","https://openalex.org/W4220714703","https://openalex.org/W2098758514","https://openalex.org/W2735929803","https://openalex.org/W3008845055","https://openalex.org/W2170391450","https://openalex.org/W4376854386","https://openalex.org/W2202724490","https://openalex.org/W2508671622"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,10,78,111,135,180,187,208],"practical":[3],"consequences":[4,63],"of":[5,13,25,80,87,114,153,211],"dataset":[6,42,90],"sampling":[7,40,58,81,105,136,205],"strategies":[8],"on":[9,23,64,82,186],"ranking":[11],"performance":[12,113,145,175],"recommendation":[14],"algorithms.":[15],"Recommender":[16],"systems":[17],"are":[18,29],"generally":[19],"trained":[20],"and":[21,89,118,126,166,184],"evaluated":[22],"samples":[24],"larger":[26],"datasets.":[27],"Samples":[28],"often":[30],"taken":[31],"in":[32,85],"a":[33,41,103,147],"naive":[34],"or":[35,44,48],"ad-hoc":[36],"fashion:":[37],"e.g.":[38],"by":[39,45],"randomly":[43],"selecting":[46],"users":[47],"items":[49],"with":[50,207],"many":[51],"interactions.":[52],"As":[53],"we":[54,196],"demonstrate,":[55],"commonly-used":[56],"data":[57,202],"schemes":[59],"can":[60,133,197],"have":[61],"significant":[62],"algorithm":[65,83,88,174,181],"performance.":[66,212],"Following":[67],"this":[68,70],"observation,":[69],"paper":[71],"makes":[72],"three":[73],"main":[74,151],"contributions:":[75],"(1)":[76],"characterizing":[77],"effect":[79],"performance,":[84],"terms":[86],"characteristics":[91],"(e.g.":[92],"sparsity":[93],"characteristics,":[94],"sequential":[95],"dynamics,":[96],"etc.);":[97],"(2)":[98],"designing":[99],"SVP-CF,":[100],"which":[101,132],"is":[102,119,139,155,182],"data-specific":[104],"strategy,":[106],"that":[107,138,156,173,193],"aims":[108],"to":[109,122,142,163],"preserve":[110,143],"relative":[112],"models":[115],"after":[116],"sampling,":[117],"especially":[120],"suited":[121],"long-tailed":[123],"interaction":[124],"data;":[125],"(3)":[127],"developing":[128],"an":[129],"oracle,":[130],"DATA-GENIE,":[131,195],"suggest":[134],"scheme":[137],"most":[140],"likely":[141],"model":[144],"for":[146],"given":[148],"dataset.":[149],"The":[150],"benefit":[152],"DATA-GENIE":[154],"it":[157],"will":[158,176],"allow":[159],"recommender":[160],"system":[161],"practitioners":[162],"quickly":[164],"prototype":[165],"compare":[167],"various":[168],"approaches,":[169],"while":[170],"remaining":[171],"confident":[172],"be":[177],"preserved,":[178],"once":[179],"retrained":[183],"deployed":[185],"complete":[188],"data.":[189],"Detailed":[190],"experiments":[191],"show":[192],"using":[194],"discard":[198],"upto":[199],"5x":[200],"more":[201],"than":[203],"any":[204],"strategy":[206],"same":[209],"level":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}