{"id":"https://openalex.org/W4368618431","doi":"https://doi.org/10.1145/3577193.3593717","title":"HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs","display_name":"HEAT: A Highly Efficient and Affordable Training System for Collaborative Filtering Based Recommendation on CPUs","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4368618431","doi":"https://doi.org/10.1145/3577193.3593717"},"language":"en","primary_location":{"id":"doi:10.1145/3577193.3593717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"preprint","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/A5100691056","display_name":"Chengming Zhang","orcid":"https://orcid.org/0000-0003-3008-9133"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengming Zhang","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3008-9133","affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089950471","display_name":"Shaden Smith","orcid":"https://orcid.org/0000-0003-4072-9990"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaden Smith","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4072-9990","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004397575","display_name":"Baixi Sun","orcid":"https://orcid.org/0000-0001-9807-7978"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baixi Sun","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-9807-7978","affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064166827","display_name":"Jiannan Tian","orcid":"https://orcid.org/0000-0003-1101-9148"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiannan Tian","raw_affiliation_strings":["Indiana University, Bloomington, IN, United States"],"raw_orcid":"https://orcid.org/0000-0003-1101-9148","affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, United States","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033869334","display_name":"Jonathan Soifer","orcid":"https://orcid.org/0009-0000-4381-1899"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Soifer","raw_affiliation_strings":["Microsoft, Redmond, United States of America"],"raw_orcid":"https://orcid.org/0009-0000-4381-1899","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052001478","display_name":"Xiaodong Yu","orcid":"https://orcid.org/0000-0001-6244-1264"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Yu","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6244-1264","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8402-1436","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040302174","display_name":"Yuxiong He","orcid":"https://orcid.org/0000-0003-0478-8854"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiong He","raw_affiliation_strings":["Microsoft, Redmond, WA, United States"],"raw_orcid":"https://orcid.org/0000-0003-0478-8854","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063703614","display_name":"Dingwen Tao","orcid":"https://orcid.org/0000-0001-5422-4497"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingwen Tao","raw_affiliation_strings":["Indiana University, Bloomington, United States"],"raw_orcid":"https://orcid.org/0000-0001-5422-4497","affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, United States","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63822414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9829000234603882,"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":0.9506999850273132,"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":0.8749878406524658},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8639110922813416},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7542997598648071},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5166569352149963},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5129756331443787},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4874017834663391},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4162633419036865},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.41466227173805237},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29532819986343384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12863978743553162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8749878406524658},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8639110922813416},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7542997598648071},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5166569352149963},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5129756331443787},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4874017834663391},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4162633419036865},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.41466227173805237},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29532819986343384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12863978743553162},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577193.3593717","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1139185857","https://openalex.org/W1533861849","https://openalex.org/W2032117234","https://openalex.org/W2042281163","https://openalex.org/W2054141820","https://openalex.org/W2071039340","https://openalex.org/W2080320419","https://openalex.org/W2115338030","https://openalex.org/W2138243089","https://openalex.org/W2138621090","https://openalex.org/W2141033972","https://openalex.org/W2155106456","https://openalex.org/W2297086932","https://openalex.org/W2408663442","https://openalex.org/W2512971201","https://openalex.org/W2565948352","https://openalex.org/W2605246672","https://openalex.org/W2642043218","https://openalex.org/W2741249238","https://openalex.org/W2808673205","https://openalex.org/W2892821876","https://openalex.org/W2893359107","https://openalex.org/W2945827670","https://openalex.org/W2998431760","https://openalex.org/W3045200674","https://openalex.org/W3100278010","https://openalex.org/W3130554079","https://openalex.org/W3203926743","https://openalex.org/W4205390421","https://openalex.org/W4251640158","https://openalex.org/W4296591817","https://openalex.org/W4297971002","https://openalex.org/W4365800003","https://openalex.org/W6667616612","https://openalex.org/W6787584414"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2966297898","https://openalex.org/W2955229517"],"abstract_inverted_index":{"Collaborative":[0],"filtering":[1],"(CF)":[2],"has":[3],"been":[4],"proven":[5],"to":[6,50,123,158,181,202],"be":[7],"one":[8],"of":[9,35,63,107,113,149],"the":[10,22,101,111,120,154,174,178],"most":[11],"effective":[12],"techniques":[13],"for":[14,162],"recommendation.":[15],"Among":[16],"all":[17],"CF":[18,93],"approaches,":[19],"SimpleX":[20,45,65],"is":[21,40,115],"state-of-the-art":[23],"method":[24],"that":[25,43,98,198],"adopts":[26],"a":[27,32],"novel":[28],"loss":[29],"function":[30],"and":[31,61,67,81,104,127,166,194,209,212],"proper":[33],"number":[34],"negative":[36],"samples.":[37],"However,":[38],"there":[39],"no":[41],"work":[42],"optimizes":[44,137],"on":[46,186],"multi-core":[47],"CPUs,":[48],"leading":[49],"limited":[51],"performance.":[52],"To":[53,85],"this":[54],"end,":[55],"we":[56,89],"perform":[57],"an":[58,91],"in-depth":[59],"profiling":[60],"analysis":[62],"existing":[64,206,219],"implementations":[66],"identify":[68],"their":[69],"performance":[70],"bottlenecks":[71],"including":[72],"(1)":[73,117],"irregular":[74],"memory":[75,79,160],"accesses,":[76],"(2)":[77,135],"unnecessary":[78],"copies,":[80],"(3)":[82,167],"redundant":[83,183],"computations.":[84],"address":[86],"these":[87],"issues,":[88],"propose":[90],"efficient":[92],"training":[94],"system":[95],"(called":[96],"HEAT)":[97],"fully":[99],"enables":[100],"multi-level":[102],"caching":[103],"multi-threading":[105],"capabilities":[106],"modern":[108],"CPUs.":[109],"Specifically,":[110],"optimization":[112],"HEAT":[114,199],"threefold:":[116],"It":[118,136,168],"tiles":[119],"embedding":[121],"matrix":[122,163],"increase":[124],"data":[125,164],"locality":[126],"reduce":[128],"cache":[129],"misses":[130],"(thus":[131],"reduces":[132],"read":[133],"latency);":[134],"stochastic":[138],"gradient":[139],"descent":[140],"(SGD)":[141],"with":[142,191,222],"sampling":[143],"by":[144],"parallelizing":[145],"vector":[146],"products":[147],"instead":[148],"matrix-matrix":[150],"multiplications,":[151],"in":[152,177,216],"particular":[153],"similarity":[155],"computation":[156],"therein,":[157],"avoid":[159],"copies":[161],"preparation;":[165],"aggressively":[169],"reuses":[170],"intermediate":[171],"results":[172],"from":[173],"forward":[175],"phase":[176,180],"backward":[179],"alleviate":[182],"computation.":[184],"Evaluation":[185],"five":[187],"widely":[188],"used":[189],"datasets":[190],"both":[192],"x86-":[193],"ARM-architecture":[195],"processors":[196],"shows":[197],"achieves":[200],"up":[201],"45.2\u00d7":[203],"speedup":[204,211],"over":[205,218],"CPU":[207],"solution":[208,221],"4.5\u00d7":[210],"7.9\u00d7":[213],"cost":[214],"reduction":[215],"Cloud":[217],"GPU":[220],"NVIDIA":[223],"V100":[224],"GPU.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}