{"id":"https://openalex.org/W4405194916","doi":"https://doi.org/10.1145/3704923","title":"Reinforcement Learning for Intra- & Inter-Node Recommender Data Pipeline Optimization","display_name":"Reinforcement Learning for Intra- & Inter-Node Recommender Data Pipeline Optimization","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405194916","doi":"https://doi.org/10.1145/3704923"},"language":"en","primary_location":{"id":"doi:10.1145/3704923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704923","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704923","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704923","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029753236","display_name":"Kabir Nagrecha","orcid":"https://orcid.org/0000-0002-0214-4812"},"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"]},{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kabir Nagrecha","raw_affiliation_strings":["Computer Science & Engineering, University of California San Diego, La Jolla, United States and Machine Learning Platform, Netflix Inc, Los Gatos, United States","Machine Learning Platform, Netflix Inc, Los Gatos, United States","Computer Science & Engineering, University of California San Diego, La Jolla, United States"],"raw_orcid":"https://orcid.org/0000-0002-0214-4812","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, University of California San Diego, La Jolla, United States and Machine Learning Platform, Netflix Inc, Los Gatos, United States","institution_ids":["https://openalex.org/I869089601"]},{"raw_affiliation_string":"Machine Learning Platform, Netflix Inc, Los Gatos, United States","institution_ids":["https://openalex.org/I869089601"]},{"raw_affiliation_string":"Computer Science & Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019093506","display_name":"Lingyi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingyi Liu","raw_affiliation_strings":["Machine Learning Platform, Netflix Inc, Los Gatos, United States"],"raw_orcid":"https://orcid.org/0009-0004-1948-6407","affiliations":[{"raw_affiliation_string":"Machine Learning Platform, Netflix Inc, Los Gatos, United States","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114985924","display_name":"Pablo Delgado","orcid":"https://orcid.org/0009-0009-7783-9035"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pablo Delgado","raw_affiliation_strings":["Machine Learning Platform, Netflix Inc, Los Gatos, United States"],"raw_orcid":"https://orcid.org/0009-0009-7783-9035","affiliations":[{"raw_affiliation_string":"Machine Learning Platform, Netflix Inc, Los Gatos, United States","institution_ids":["https://openalex.org/I869089601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33621829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9951000213623047,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9937000274658203,"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":0.8167529106140137},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8103143572807312},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6487793326377869},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6335663795471191},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6192551851272583},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.554739236831665},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5224496722221375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4206570088863373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40515223145484924},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37358877062797546},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3610760569572449},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10226684808731079},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09113618731498718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167529106140137},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8103143572807312},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6487793326377869},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6335663795471191},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6192551851272583},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.554739236831665},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5224496722221375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4206570088863373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40515223145484924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37358877062797546},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3610760569572449},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10226684808731079},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09113618731498718},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704923","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704923","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3704923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704923","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704923","source":{"id":"https://openalex.org/S4387284325","display_name":"ACM Transactions on Recommender Systems","issn_l":"2770-6699","issn":["2770-6699"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Recommender Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5799999833106995,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405194916.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1990687271","https://openalex.org/W2102558581","https://openalex.org/W2475334473","https://openalex.org/W2613206411","https://openalex.org/W2751448157","https://openalex.org/W2765982206","https://openalex.org/W2772526503","https://openalex.org/W2790625403","https://openalex.org/W2798515322","https://openalex.org/W2901299405","https://openalex.org/W2970148517","https://openalex.org/W2973727699","https://openalex.org/W2979245724","https://openalex.org/W2991040477","https://openalex.org/W3016842236","https://openalex.org/W3037847693","https://openalex.org/W3040573126","https://openalex.org/W3041449006","https://openalex.org/W3099158806","https://openalex.org/W3099273181","https://openalex.org/W3121689374","https://openalex.org/W3123457082","https://openalex.org/W3130395060","https://openalex.org/W3137813374","https://openalex.org/W3158146252","https://openalex.org/W3161161408","https://openalex.org/W3163790871","https://openalex.org/W3174394143","https://openalex.org/W3177342429","https://openalex.org/W3185381167","https://openalex.org/W3188694252","https://openalex.org/W3196732841","https://openalex.org/W3200664681","https://openalex.org/W3208860256","https://openalex.org/W3211937550","https://openalex.org/W4214658871","https://openalex.org/W4220938834","https://openalex.org/W4223433508","https://openalex.org/W4225854672","https://openalex.org/W4281657584","https://openalex.org/W4281758439","https://openalex.org/W4281890931","https://openalex.org/W4287724000","https://openalex.org/W4288267707","https://openalex.org/W4289703391","https://openalex.org/W4293775467","https://openalex.org/W4296591836","https://openalex.org/W4296591840","https://openalex.org/W4301314773","https://openalex.org/W4304091391","https://openalex.org/W4386729362","https://openalex.org/W4388041378","https://openalex.org/W4392454234","https://openalex.org/W6748170970","https://openalex.org/W6769062451"],"related_works":["https://openalex.org/W4380433113","https://openalex.org/W2359178629","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2375218795","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2071821326","https://openalex.org/W2051877971"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"recommender":[2,13,124],"models":[3],"(DLRMs)":[4],"have":[5],"become":[6],"an":[7],"essential":[8],"component":[9],"of":[10,92,133,205],"many":[11],"modern":[12],"systems.":[14],"Several":[15],"companies":[16],"are":[17,42,51],"now":[18],"building":[19],"large":[20],"compute":[21,83],"clusters":[22],"reserved":[23],"for":[24,112,121],"DLRM":[25,62,76],"training,":[26],"driving":[27],"new":[28,110],"interest":[29],"in":[30,39,61,98],"cost-":[31],"and":[32,95,129,136,159,183],"time-saving":[33],"optimizations.":[34],"The":[35],"systems":[36],"challenges":[37,132],"faced":[38],"this":[40,71,143],"setting":[41],"unique;":[43],"while":[44,201],"typical":[45],"deep":[46],"learning":[47,148],"(DL)":[48],"training":[49,63],"jobs":[50],"dominated":[52],"by":[53,192,208],"model":[54],"execution":[55],"times,":[56],"the":[57,89,131,156,203],"most":[58],"important":[59],"factor":[60],"performance":[64,90],"is":[65,119],"often":[66],"online":[67,93],"data":[68,77,100,113,125,172,189],"ingestion.":[69],"In":[70],"article,":[72],"we":[73],"study":[74],"real-world":[75],"processing":[78],"pipelines":[79,207],"taken":[80],"from":[81],"our":[82,181],"cluster":[84,157,182],"at":[85,155],"Netflix":[86],"to":[87,107,180,210],"observe":[88],"impacts":[91],"ingestion":[94,190],"identify":[96],"shortfalls":[97],"existing":[99],"pipeline":[101,114,139,173],"optimizers.":[102],"Our":[103,164],"studies":[104],"lead":[105],"us":[106],"design":[108],"a":[109,145],"solution":[111],"optimization,":[115],"InTuneX":[116,118,168,179],".":[117],"designed":[120],"production-scale":[122],"multi-node":[123,206],"pipelines.":[126],"It":[127],"unifies":[128],"tackles":[130],"both":[134],"intra-":[135],"inter-":[137],"node":[138,153],"optimization.":[140],"We":[141,177],"achieve":[142],"with":[144],"multi-agent":[146],"reinforcement":[147],"(RL)":[149],"design,":[150],"simultaneously":[151],"optimizing":[152],"assignments":[154,161],"level":[158],"CPU":[160],"within":[162,175],"nodes.":[163],"experiments":[165],"show":[166],"that":[167,185],"can":[169],"build":[170],"optimized":[171],"configurations":[174],"minutes.":[176],"apply":[178],"find":[184],"it":[186],"increases":[187],"single-node":[188],"throughput":[191],"as":[193,195],"much":[194],"2.29":[196],"\u00d7":[197],"versus":[198],"state-of-the-art":[199],"optimizers,":[200],"improving":[202],"cost-efficiency":[204],"15%":[209],"25%.":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}