{"id":"https://openalex.org/W4404310918","doi":"https://doi.org/10.48550/arxiv.2410.18111","title":"Data Efficiency for Large Recommendation Models","display_name":"Data Efficiency for Large Recommendation Models","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4404310918","doi":"https://doi.org/10.48550/arxiv.2410.18111"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.18111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18111","pdf_url":"https://arxiv.org/pdf/2410.18111","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.18111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103231054","display_name":"Kshitij Jain","orcid":"https://orcid.org/0000-0002-5515-132X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jain, Kshitij","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Jingru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jingru","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078411059","display_name":"Kevin Regan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regan, Kevin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420607","display_name":"Cheng Chen","orcid":"https://orcid.org/0009-0007-5152-7194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439065","display_name":"Jie Han","orcid":"https://orcid.org/0000-0002-3029-2476"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110604838","display_name":"Steve Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Steve","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082749498","display_name":"Zhuoshu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhuoshu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060118256","display_name":"Todd Phillips","orcid":"https://orcid.org/0000-0001-7382-5191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phillips, Todd","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sussman, Myles","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sussman, Myles","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114619027","display_name":"Matt Troup","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Troup, Matt","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043651637","display_name":"\u963f\u90e8 \u88d5","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Angel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhuo, Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo, Jia","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5103231054"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9829999804496765,"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":0.9829999804496765,"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":0.5481324195861816},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.349284291267395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34908774495124817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5481324195861816},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.349284291267395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34908774495124817}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.18111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18111","pdf_url":"https://arxiv.org/pdf/2410.18111","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.18111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.18111","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.18111","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.18111","pdf_url":"https://arxiv.org/pdf/2410.18111","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404310918.pdf","grobid_xml":"https://content.openalex.org/works/W4404310918.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"recommendation":[1],"models":[2,85],"(LRMs)":[3],"are":[4,87],"fundamental":[5],"to":[6,24,28,30,65,101,109],"the":[7,46,94],"multi-billion":[8],"dollar":[9],"online":[10,26],"advertising":[11],"industry,":[12],"processing":[13],"massive":[14,36],"datasets":[15],"of":[16,18,20,38,96],"hundreds":[17],"billions":[19],"examples":[21],"before":[22],"transitioning":[23],"continuous":[25],"training":[27,70,112],"adapt":[29],"rapidly":[31],"changing":[32],"user":[33],"behavior.":[34],"The":[35],"scale":[37],"data":[39,71,97,113],"directly":[40],"impacts":[41],"both":[42],"computational":[43],"costs":[44],"and":[45,62,86,105],"speed":[47],"at":[48],"which":[49],"new":[50],"methods":[51,100],"can":[52],"be":[53],"evaluated":[54],"(R&D":[55],"velocity).":[56],"This":[57],"paper":[58],"presents":[59],"actionable":[60],"principles":[61],"high-level":[63],"frameworks":[64],"guide":[66],"practitioners":[67],"in":[68,79],"optimizing":[69],"requirements.":[72],"These":[73],"strategies":[74],"have":[75],"been":[76],"successfully":[77],"deployed":[78],"Google's":[80],"largest":[81],"Ads":[82],"CTR":[83],"prediction":[84],"broadly":[88],"applicable":[89],"beyond":[90],"LRMs.":[91],"We":[92],"outline":[93],"concept":[95],"convergence,":[98,104],"describe":[99],"accelerate":[102],"this":[103],"finally,":[106],"detail":[107],"how":[108],"optimally":[110],"balance":[111],"volume":[114],"with":[115],"model":[116],"size.":[117]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}