{"id":"https://openalex.org/W4403220464","doi":"https://doi.org/10.1145/3640457.3688052","title":"Improving Data Efficiency for Recommenders and LLMs","display_name":"Improving Data Efficiency for Recommenders and LLMs","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403220464","doi":"https://doi.org/10.1145/3640457.3688052"},"language":"en","primary_location":{"id":"doi:10.1145/3640457.3688052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688052","any_repository_has_fulltext":null},"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/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noveen Sachdeva","raw_affiliation_strings":["Google DeepMind, Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0000-0003-1228-746X","affiliations":[{"raw_affiliation_string":"Google DeepMind, Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082158416","display_name":"Benjamin Coleman","orcid":"https://orcid.org/0009-0001-8045-3717"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Coleman","raw_affiliation_strings":["Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0009-0001-8045-3717","affiliations":[{"raw_affiliation_string":"Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090597599","display_name":"Wang-Cheng Kang","orcid":"https://orcid.org/0009-0006-8795-3665"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Cheng Kang","raw_affiliation_strings":["n/a, Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0009-0006-8795-3665","affiliations":[{"raw_affiliation_string":"n/a, Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077817759","display_name":"Jianmo Ni","orcid":"https://orcid.org/0000-0002-6863-8073"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianmo Ni","raw_affiliation_strings":["Deepmind, Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0000-0002-6863-8073","affiliations":[{"raw_affiliation_string":"Deepmind, Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048489384","display_name":"James Caverlee","orcid":"https://orcid.org/0000-0001-8350-8528"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Caverlee","raw_affiliation_strings":["Computer Science and Engineering, Texas A&M University, USA"],"raw_orcid":"https://orcid.org/0000-0001-8350-8528","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Texas A&M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079085366","display_name":"Lichan Hong","orcid":"https://orcid.org/0009-0004-9563-554X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichan Hong","raw_affiliation_strings":["Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0009-0004-9563-554X","affiliations":[{"raw_affiliation_string":"Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028125399","display_name":"Ed H.","orcid":"https://orcid.org/0000-0003-3230-5338"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ed Chi","raw_affiliation_strings":["Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0000-0003-3230-5338","affiliations":[{"raw_affiliation_string":"Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055484401","display_name":"Derek Zhiyuan Cheng","orcid":"https://orcid.org/0009-0000-7943-8328"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Zhiyuan Cheng","raw_affiliation_strings":["Google DeepMind, Google DeepMind, USA"],"raw_orcid":"https://orcid.org/0009-0000-7943-8328","affiliations":[{"raw_affiliation_string":"Google DeepMind, Google DeepMind, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"790","last_page":"792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9865000247955322,"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/T11719","display_name":"Data Quality and Management","score":0.9865000247955322,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9232000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5091425776481628},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33451366424560547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5091425776481628},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33451366424560547}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3640457.3688052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3640457.3688052","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640457.3688052","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640457.3688052","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403220464.pdf"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4283761305"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"massive":[3,31],"transformer-based":[4],"architectures":[5],"have":[6],"driven":[7],"breakthrough":[8],"performance":[9],"in":[10,212],"practical":[11],"applications":[12],"like":[13],"autoregressive":[14],"text-generation":[15],"(LLMs)":[16],"and":[17,47,67,78,98,121,143,177,206],"click-prediction":[18],"(recommenders).":[19],"A":[20],"common":[21],"recipe":[22],"for":[23,119,194],"success":[24],"is":[25,134],"to":[26,63,86,189],"train":[27],"large":[28],"models":[29,123],"on":[30,41,51,203],"web-scale":[32,213],"datasets":[33],"[3,":[34],"15],":[35],"e.g.,":[36],"modern":[37],"recommenders":[38],"are":[39,49,61,187],"trained":[40,50],"billions":[42],"of":[43,53,70,75,84,94,102,116,148,171,228],"user-item":[44],"click":[45],"events,":[46],"LLMs":[48],"trillions":[52],"tokens":[54],"extracted":[55],"from":[56,88,156],"the":[57,65,73,81,95,103,146,149,172,191,204,220,225],"public":[58],"internet.":[59],"We":[60,153],"close":[62],"hitting":[64],"computational":[66],"economical":[68],"limits":[69],"scaling":[71],"up":[72],"size":[74],"these":[76],"models,":[77,142],"we":[79,112],"expect":[80],"next":[82],"frontier":[83],"gains":[85],"come":[87],"improving":[89],"the:":[90],"(i)":[91,136,161],"data":[92,100,131,159,162,179,210],"quality":[93,141],"training":[96,106,151,195],"dataset,":[97],"(ii)":[99,144,178],"efficiency":[101],"extremely":[104],"expensive":[105],"procedure.":[107,152],"Inspired":[108],"by":[109,209],"this":[110,199],"shift,":[111],"present":[113],"a":[114,126,129,215],"set":[115],"\u201cdata-centric\u201d":[117],"techniques":[118,155,181],"recommendation":[120,221],"language":[122],"that":[124,168,182],"summarizes":[125],"dataset":[127,173],"into":[128],"terse":[130],"summary,":[132],"which":[133,186],"both":[135],"high-quality,":[137],"i.e.,":[138],"trains":[139],"better":[140],"improves":[145],"data-efficiency":[147],"overall":[150],"propose":[154],"two":[157],"disparate":[158],"frameworks:":[160],"selection":[163],"(a.k.a.,":[164],"coreset":[165],"construction)":[166],"methods":[167],"sample":[169],"portions":[170],"using":[174],"grounded":[175],"heuristics,":[176],"distillation":[180],"generate":[183],"synthetic":[184],"examples":[185],"optimized":[188],"retain":[190],"signals":[192],"needed":[193],"high-quality":[196],"models.":[197],"Overall,":[198],"work":[200],"sheds":[201],"light":[202],"challenges":[205],"opportunities":[207],"offered":[208],"optimization":[211],"systems,":[214],"particularly":[216],"relevant":[217],"focus":[218],"as":[219],"community":[222],"grapples":[223],"with":[224],"grand":[226],"challenge":[227],"leveraging":[229],"LLMs.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}