{"id":"https://openalex.org/W2962836134","doi":"https://doi.org/10.1109/tpds.2019.2904058","title":"Parallelizing Word2Vec in Shared and Distributed Memory","display_name":"Parallelizing Word2Vec in Shared and Distributed Memory","publication_year":2019,"publication_date":"2019-03-08","ids":{"openalex":"https://openalex.org/W2962836134","doi":"https://doi.org/10.1109/tpds.2019.2904058","mag":"2962836134"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2904058","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/1604.04661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036338045","display_name":"Shihao Ji","orcid":"https://orcid.org/0000-0002-3573-5379"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"funder","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihao Ji","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA, USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111985072","display_name":"Nadathur Satish","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nadathur Satish","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032238070","display_name":"Pradeep Dubey","orcid":"https://orcid.org/0000-0001-5853-0619"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"funder","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pradeep K. Dubey","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.489,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":63,"citation_normalized_percentile":{"value":0.999973,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"30","issue":"9","first_page":"2090","last_page":"2100"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9955,"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/word2vec","display_name":"Word2vec","score":0.93901896},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.49357307},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.42213193}],"concepts":[{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.93901896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9048867},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.64988095},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6200549},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49357307},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47905385},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.42213193},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4205989},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.35253084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3433897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28163362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21110791},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14054003},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09463361},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2904058","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.04661","pdf_url":"http://arxiv.org/pdf/1604.04661","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.04661","pdf_url":"http://arxiv.org/pdf/1604.04661","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.51,"id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1574901103","https://openalex.org/W1614298861","https://openalex.org/W1902237438","https://openalex.org/W1994616650","https://openalex.org/W2053921957","https://openalex.org/W2060393849","https://openalex.org/W2083842231","https://openalex.org/W2103318667","https://openalex.org/W2117130368","https://openalex.org/W2130942839","https://openalex.org/W2131494463","https://openalex.org/W2138204974","https://openalex.org/W2138243089","https://openalex.org/W2146502635","https://openalex.org/W2149381887","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2202715214","https://openalex.org/W2549505656","https://openalex.org/W2611669587","https://openalex.org/W2757910899","https://openalex.org/W2773689216","https://openalex.org/W2962769333","https://openalex.org/W2963959597","https://openalex.org/W2964091467","https://openalex.org/W3216404684","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W796926850"],"related_works":["https://openalex.org/W4245497162","https://openalex.org/W4205439893","https://openalex.org/W2353146130","https://openalex.org/W2264746079","https://openalex.org/W2150064838","https://openalex.org/W2026512611","https://openalex.org/W1990817968","https://openalex.org/W1987160526","https://openalex.org/W1985165680","https://openalex.org/W1933089384"],"abstract_inverted_index":{"Word2vec":[0],"is":[1,114,151],"a":[2,99],"widely":[3],"used":[4],"algorithm":[5,66,113],"for":[6,27,117,167],"extracting":[7],"low-dimensional":[8],"vector":[9],"representations":[10],"of":[11,60,70,144,146,159],"words.":[12],"State-of-the-art":[13],"algorithms":[14],"including":[15],"those":[16],"by":[17,57],"Mikolov":[18],"et":[19],"al.":[20],"[1]":[21],",":[22],"[2]":[23],"have":[24],"been":[25],"parallelized":[26],"multi-core":[28],"CPU":[29],"architectures,":[30,120],"but":[31],"are":[32,41],"based":[33],"on":[34],"vector-vector":[35],"operations":[36],"with":[37],"\"Hogwild\"":[38],"updates":[39],"that":[40],"memory-bandwidth":[42],"intensive":[43],"and":[44,72,102,127,139,141,170],"do":[45],"not":[46],"efficiently":[47],"use":[48,69],"computational":[49],"resources.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"\"HogBatch\"":[56],"improving":[58],"reuse":[59],"various":[61],"data":[62],"structures":[63],"in":[64,98],"the":[65,68,81,133,152,157,164],"through":[67],"minibatching":[71],"negative":[73],"sample":[74],"sharing,":[75],"hence":[76],"allowing":[77],"us":[78,129],"to":[79,92,108,130,156],"express":[80],"problem":[82],"using":[83],"matrix":[84],"multiply":[85],"operations.":[86],"We":[87,162],"also":[88],"explore":[89],"different":[90],"techniques":[91],"distribute":[93],"word2vec":[94,154],"computation":[95,134],"across":[96,137],"nodes":[97],"computer":[100],"cluster,":[101],"demonstrate":[103],"good":[104],"strong":[105],"scalability":[106],"up":[107,132],"32":[109],"nodes.":[110],"The":[111],"new":[112],"particularly":[115],"suitable":[116],"modern":[118],"multi-core/many-core":[119],"especially":[121],"Intel's":[122],"latest":[123],"Knights":[124],"Landing":[125],"processors,":[126],"allows":[128],"scale":[131],"near":[135],"linearly":[136],"cores":[138],"nodes,":[140],"process":[142],"hundreds":[143],"millions":[145],"words":[147],"per":[148],"second,":[149],"which":[150],"fastest":[153],"implementation":[155],"best":[158],"our":[160],"knowledge.":[161],"released":[163],"source":[165],"code":[166],"reproducible":[168],"research":[169],"general":[171],"usage.":[172]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2962836134","counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2025-04-18T19:36:59.629426","created_date":"2019-07-30"}