{"id":"https://openalex.org/W4394969333","doi":"https://doi.org/10.1145/3642970.3655825","title":"Evaluating Deep Learning Recommendation Model Training Scalability with the Dynamic Opera Network","display_name":"Evaluating Deep Learning Recommendation Model Training Scalability with the Dynamic Opera Network","publication_year":2024,"publication_date":"2024-04-19","ids":{"openalex":"https://openalex.org/W4394969333","doi":"https://doi.org/10.1145/3642970.3655825"},"language":"en","primary_location":{"id":"doi:10.1145/3642970.3655825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3642970.3655825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003773058","display_name":"Connor Imes","orcid":"https://orcid.org/0000-0003-1683-8353"},"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":"Connor Imes","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073069762","display_name":"Andrew Rittenbach","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":false,"raw_author_name":"Andrew Rittenbach","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053577072","display_name":"Peng Xie","orcid":"https://orcid.org/0009-0002-4744-0110"},"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":"Peng Xie","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053947268","display_name":"Dong In D. Kang","orcid":"https://orcid.org/0009-0004-6232-6863"},"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":"Dong In D. Kang","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023774940","display_name":"John Paul Walters","orcid":"https://orcid.org/0000-0001-5281-6237"},"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":"John Paul Walters","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022935102","display_name":"Stephen P. Crago","orcid":"https://orcid.org/0000-0002-5620-4227"},"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":"Stephen P. Crago","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Arlington, VA, USA and Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Arlington, VA, USA and Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003773058"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06568067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9944999814033508,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8480973243713379},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8113256096839905},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6672863960266113},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5493504405021667},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5390228033065796},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5173846483230591},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5112831592559814},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4997060298919678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49860262870788574},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46131134033203125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4510084390640259},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4465215802192688},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4277067184448242},{"id":"https://openalex.org/keywords/opera","display_name":"Opera","score":0.4104555547237396},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.37550294399261475},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.321353942155838},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11089551448822021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10910981893539429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480973243713379},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8113256096839905},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6672863960266113},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5493504405021667},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5390228033065796},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5173846483230591},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5112831592559814},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4997060298919678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49860262870788574},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46131134033203125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4510084390640259},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4465215802192688},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4277067184448242},{"id":"https://openalex.org/C530479602","wikidata":"https://www.wikidata.org/wiki/Q1344","display_name":"Opera","level":2,"score":0.4104555547237396},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.37550294399261475},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.321353942155838},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11089551448822021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10910981893539429},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3642970.3655825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3642970.3655825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th Workshop on Machine Learning and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2057332538","https://openalex.org/W2141810662","https://openalex.org/W2210543184","https://openalex.org/W2486960733","https://openalex.org/W2512971201","https://openalex.org/W2743429249","https://openalex.org/W2744387122","https://openalex.org/W3016842236","https://openalex.org/W3130104841","https://openalex.org/W3173720884","https://openalex.org/W3197720002"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W2741781807"],"abstract_inverted_index":{"Deep":[0],"learning":[1,19],"is":[2,24,72,128],"commonly":[3],"used":[4],"to":[5,9,41,74,100,106,130],"make":[6],"personalized":[7],"recommendations":[8],"users":[10],"for":[11,47],"a":[12,36],"wide":[13,37],"variety":[14,38],"of":[15,39],"activities.":[16],"However,":[17],"deep":[18],"recommendation":[20],"model":[21,63,93],"(DLRM)":[22],"training":[23,64,94,121,132],"increasingly":[25],"dominated":[26],"by":[27,56],"all-to-all":[28],"and":[29,45,103,123],"many-to-many":[30],"communication":[31,44],"patterns.":[32],"While":[33],"there":[34],"are":[35,53],"algorithms":[40],"efficiently":[42],"overlap":[43],"computation":[46],"many":[48],"collective":[49],"operations,":[50],"these":[51],"patterns":[52],"strictly":[54],"limited":[55],"network":[57,77],"bottlenecks.":[58],"We":[59,116],"propose":[60],"co-designing":[61],"DLRM":[62,92],"with":[65,112],"the":[66],"recently":[67],"proposed":[68],"Opera":[69,110],"network,":[70],"which":[71],"designed":[73],"avoid":[75],"multiple":[76],"hops":[78],"using":[79,109],"time-varying":[80],"source-to-destination":[81],"circuits.":[82],"Using":[83],"measurements":[84],"from":[85,98],"state-of-the-art":[86],"NVIDIA":[87],"A100":[88],"GPUs,":[89],"we":[90],"simulate":[91],"on":[95],"networks":[96],"ranging":[97],"16":[99],"1024":[101],"nodes":[102],"demonstrate":[104,124],"up":[105],"1.79\u00d7":[107],"improvement":[108],"compared":[111],"equivalent":[113],"fat-tree":[114],"networks.":[115],"identify":[117],"important":[118],"parameters":[119],"affecting":[120],"time":[122],"that":[125],"careful":[126],"co-design":[127],"needed":[129],"optimize":[131],"latency.":[133]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}