{"id":"https://openalex.org/W4414034929","doi":"https://doi.org/10.1145/3705328.3748078","title":"LEAF: Lightweight, Efficient, Adaptive and Flexible Embedding for Large-Scale Recommendation Models","display_name":"LEAF: Lightweight, Efficient, Adaptive and Flexible Embedding for Large-Scale Recommendation Models","publication_year":2025,"publication_date":"2025-09-06","ids":{"openalex":"https://openalex.org/W4414034929","doi":"https://doi.org/10.1145/3705328.3748078"},"language":"en","primary_location":{"id":"doi:10.1145/3705328.3748078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3705328.3748078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3705328.3748078","source":null,"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 Nineteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3705328.3748078","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052218561","display_name":"Chaoyi Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaoyi Jiang","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0008-8235-9303","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007990050","display_name":"Abdulla Alshabanah","orcid":"https://orcid.org/0009-0009-7619-874X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdulla Alshabanah","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0009-0009-7619-874X","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018033573","display_name":"Murali Annavaram","orcid":"https://orcid.org/0000-0002-4633-6867"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Annavaram","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-4633-6867","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052218561"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.342161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"217","last_page":"225"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7133645415306091},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6647301316261292},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6131051182746887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31869572401046753},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0777258574962616},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06966668367385864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133645415306091},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6647301316261292},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6131051182746887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31869572401046753},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0777258574962616},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06966668367385864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3705328.3748078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3705328.3748078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3705328.3748078","source":null,"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 Nineteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3705328.3748078","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3705328.3748078","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3705328.3748078","source":null,"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 Nineteenth ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1555293057","display_name":null,"funder_award_id":"HR001120C0088","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8682633387","display_name":null,"funder_award_id":"2224319","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"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414034929.pdf","grobid_xml":"https://content.openalex.org/works/W4414034929.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1956340982","https://openalex.org/W2056012370","https://openalex.org/W2060324268","https://openalex.org/W2070996757","https://openalex.org/W2080234606","https://openalex.org/W2475334473","https://openalex.org/W2512971201","https://openalex.org/W2618337091","https://openalex.org/W2898069179","https://openalex.org/W2964182926","https://openalex.org/W2972269283","https://openalex.org/W3016842236","https://openalex.org/W3081362488","https://openalex.org/W3088463703","https://openalex.org/W3100127252","https://openalex.org/W3197870239","https://openalex.org/W3201621211","https://openalex.org/W3210980860","https://openalex.org/W4214658871","https://openalex.org/W4226150639","https://openalex.org/W4382239994","https://openalex.org/W4393180038","https://openalex.org/W4394414413"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"Recommendation":[2],"Models":[3],"(DLRMs)":[4],"are":[5,78],"central":[6],"to":[7,31,51,92,133],"enhancing":[8],"user":[9,25,34],"engagement":[10],"and":[11,15,20,60,67,101,177,189],"experience":[12],"with":[13,38,181],"internet":[14],"ecommerce":[16],"companies.DLRMs":[17],"provide":[18],"content":[19],"commercial":[21],"suggestions":[22],"by":[23],"modeling":[24],"behavior.DLRMs":[26],"rely":[27],"on":[28,106,122,137,142,172],"embedding":[29,47,76,90,119],"tables":[30,49,91,120],"capture":[32],"the":[33,46,56,117,138,159],"behavior,":[35],"where":[36],"users":[37,59],"similar":[39],"interests":[40],"may":[41],"be":[42],"represented":[43],"closer":[44],"in":[45,65],"space.Embedding":[48],"scale":[50],"tens":[52],"of":[53,58,99,150,162,185,194],"terabytes":[54,98],"as":[55,75],"number":[57],"features":[61],"grows,":[62],"presenting":[63],"challenges":[64],"training":[66],"storage.These":[68],"models":[69],"typically":[70],"require":[71],"substantial":[72],"GPU":[73],"memory,":[74],"operations":[77],"not":[79],"compute-intensive":[80],"but":[81],"occupy":[82],"significant":[83,104],"storage.While":[84],"some":[85],"solutions":[86],"have":[87],"explored":[88],"offloading":[89],"CPU,":[93],"this":[94],"approach":[95],"still":[96],"demands":[97],"memory":[100],"places":[102],"a":[103,111,130,147],"burden":[105],"CPU-GPU":[107],"interconnect.We":[108],"introduce":[109],"LEAF,":[110],"multi-level":[112],"hashing":[113],"framework":[114],"that":[115,166],"compresses":[116],"large":[118],"based":[121],"real-time":[123],"access":[124,135,151],"frequency":[125],"distribution.In":[126],"particular,":[127],"LEAF":[128,157,167,195],"leverages":[129],"streaming":[131],"algorithm":[132],"estimate":[134],"distributions":[136],"fly":[139],"without":[140],"relying":[141],"model":[143],"gradients":[144],"or":[145],"requiring":[146],"priori":[148],"knowledge":[149],"distribution.By":[152],"using":[153],"multiple":[154],"hash":[155],"functions,":[156],"minimizes":[158],"collision":[160],"rates":[161],"feature":[163],"instances.Experiments":[164],"show":[165],"outperforms":[168],"stateof-the-art":[169],"compression":[170],"methods":[171],"Criteo":[173,178],"Kaggle,":[174],"Avazu,":[175],"KDD12,":[176],"Terabyte":[179],"datasets,":[180],"testing":[182],"AUC":[183],"improvements":[184],"1.411%,":[186],"1.885%,":[187],"2.761%,":[188],"1.243%,":[190],"respectively.The":[191],"source":[192],"code":[193],"is":[196],"available":[197],"at":[198],"github.com/chaoyij/LEAF.":[199]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}