{"id":"https://openalex.org/W4282576620","doi":"https://doi.org/10.1145/3514221.3517902","title":"HET-GMP: A Graph-based System Approach to Scaling Large Embedding Model Training","display_name":"HET-GMP: A Graph-based System Approach to Scaling Large Embedding Model Training","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4282576620","doi":"https://doi.org/10.1145/3514221.3517902"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517902","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","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/A5015552951","display_name":"Xupeng Miao","orcid":"https://orcid.org/0000-0002-9371-8358"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xupeng Miao","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114171391","display_name":"Yining Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yining Shi","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462441","display_name":"Hailin Zhang","orcid":"https://orcid.org/0009-0000-4188-7742"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailin Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327368","display_name":"Xin Zhang","orcid":"https://orcid.org/0000-0001-8560-5006"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059601307","display_name":"Xiaonan Nie","orcid":"https://orcid.org/0000-0001-6766-757X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaonan Nie","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102862758","display_name":"Zhi Yang","orcid":"https://orcid.org/0000-0002-8219-4499"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062357883","display_name":"Bin Cui","orcid":"https://orcid.org/0000-0003-1681-4677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cui","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5015552951"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.0875,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.8898076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9993000030517578,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9993000030517578,"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":0.9987999796867371,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9934999942779541,"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":0.7900881171226501},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6944208741188049},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6917135715484619},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5461947321891785},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.542124330997467},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4356168508529663},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.41573554277420044},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4109201729297638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27894681692123413},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17920079827308655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900881171226501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6944208741188049},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6917135715484619},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5461947321891785},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.542124330997467},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4356168508529663},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.41573554277420044},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4109201729297638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27894681692123413},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17920079827308655},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517902","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1448681276","https://openalex.org/W1986603225","https://openalex.org/W2070232376","https://openalex.org/W2096544401","https://openalex.org/W2166559705","https://openalex.org/W2475334473","https://openalex.org/W2604662567","https://openalex.org/W2723293840","https://openalex.org/W2751219672","https://openalex.org/W2793768763","https://openalex.org/W2906007643","https://openalex.org/W2998207486","https://openalex.org/W3003883635","https://openalex.org/W3030204405","https://openalex.org/W3035403290","https://openalex.org/W3086105743","https://openalex.org/W3090347762","https://openalex.org/W3104030692","https://openalex.org/W3109841242","https://openalex.org/W3125483857","https://openalex.org/W3159953606","https://openalex.org/W3166605255","https://openalex.org/W3173839890","https://openalex.org/W3177263144","https://openalex.org/W3189231572","https://openalex.org/W3194434277","https://openalex.org/W3198767952","https://openalex.org/W4226328099"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W4226299621","https://openalex.org/W3211351785"],"abstract_inverted_index":{"Embedding":[0],"models":[1,124],"have":[2],"been":[3],"recognized":[4],"as":[5,101],"an":[6,170],"effective":[7],"learning":[8],"paradigm":[9],"for":[10,125],"high-dimensional":[11],"data.":[12],"However,":[13],"a":[14,45,57,78,145,162],"major":[15],"embedding":[16,28,50,90,123,147,155],"model":[17,156],"training":[18,34,49,157],"obstacle":[19],"is":[20,70],"that":[21,152],"updating":[22],"and":[23,89,99,105,110,136,169],"retrieving":[24],"the":[25,32,71,83,119,122,132,175],"shared":[26],"large-scale":[27],"parameters":[29],"usually":[30],"dominates":[31],"distributed":[33,46],"cycle,":[35],"leading":[36],"to":[37,60,81,95,106,113,140,144,167],"significant":[38,134],"scalability":[39],"issues.":[40],"This":[41,92],"paper":[42],"presents":[43,131],"HET-GMP,":[44],"system":[47,120],"on":[48,121],"models.":[51],"Uniquely,":[52],"HET-GMP":[53,76,94,153],"takes":[54],"advantage":[55],"of":[56,74],"graph-based":[58,108],"approach":[59],"efficiently":[61],"increase":[62],"scalability.":[63],"The":[64,149],"key":[65],"insight":[66],"guiding":[67],"our":[68],"design":[69],"\"graph":[72],"way":[73],"thinking\".":[75],"creates":[77],"bigraph":[79],"abstraction":[80],"represent":[82],"access":[84,142],"relationships":[85],"between":[86],"data":[87],"samples":[88],"vectors.":[91],"enables":[93],"embrace":[96],"graph":[97],"locality":[98],"skewness":[100],"new":[102],"performance":[103],"opportunities":[104],"exploit":[107],"replication/partitioning":[109],"bounded-asynchronous":[111],"synchronization":[112],"reduce":[114],"communication":[115,137,165],"overhead.":[116],"We":[117],"evaluate":[118],"click-through":[126],"rate":[127],"(CTR)":[128],"prediction,":[129],"which":[130],"most":[133],"challenge":[135],"bottleneck":[138],"due":[139],"heavy":[141],"concurrency":[143],"huge":[146],"table.":[148],"result":[150],"shows":[151],"supports":[154],"with":[158],"1011":[159],"parameters,":[160],"achieving":[161],"reduction":[163],"in":[164],"up":[166],"87.5%":[168],"up-to":[171],"27.5x":[172],"speedup":[173],"over":[174],"state-of-the-art":[176],"baseline":[177],"systems.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}