{"id":"https://openalex.org/W4296591836","doi":"https://doi.org/10.1145/3523227.3546765","title":"A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models","display_name":"A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models","publication_year":2022,"publication_date":"2022-09-13","ids":{"openalex":"https://openalex.org/W4296591836","doi":"https://doi.org/10.1145/3523227.3546765"},"language":"en","primary_location":{"id":"doi:10.1145/3523227.3546765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546765","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546765","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056170667","display_name":"Yingcan Wei","orcid":"https://orcid.org/0000-0002-5093-7382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingcan Wei","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004952","display_name":"Matthias Langer","orcid":"https://orcid.org/0000-0003-1776-8000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Langer","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yu","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031393194","display_name":"Minseok Lee","orcid":"https://orcid.org/0000-0002-8367-1939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minseok Lee","raw_affiliation_strings":["NVIDIA, Korea, Republic of"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, Korea, Republic of","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454195","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-1983-5086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041948343","display_name":"Ji Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Shi","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020576598","display_name":"Zehuan Wang","orcid":"https://orcid.org/0000-0002-1072-2651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehuan Wang","raw_affiliation_strings":["NVIDIA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4173,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.960085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"408","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9965000152587891,"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":0.9948999881744385,"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":0.8800055980682373},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6828057169914246},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6073741316795349},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5713256597518921},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5503498911857605},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4897020161151886},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4734499156475067},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3607120215892792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35946890711784363},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3401597738265991},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.325298011302948},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14384886622428894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8800055980682373},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6828057169914246},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6073741316795349},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5713256597518921},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5503498911857605},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4897020161151886},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4734499156475067},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3607120215892792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35946890711784363},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3401597738265991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.325298011302948},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14384886622428894}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3523227.3546765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546765","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2210.08804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.08804","pdf_url":"https://arxiv.org/pdf/2210.08804","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3523227.3546765","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3523227.3546765","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3523227.3546765","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM Conference on Recommender Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296591836.pdf","grobid_xml":"https://content.openalex.org/works/W4296591836.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1864199185","https://openalex.org/W2000042664","https://openalex.org/W2110975861","https://openalex.org/W2219888463","https://openalex.org/W2339765813","https://openalex.org/W2589642470","https://openalex.org/W2792078035","https://openalex.org/W2889456810","https://openalex.org/W2947737663","https://openalex.org/W2964108773","https://openalex.org/W2972087877","https://openalex.org/W2984100107","https://openalex.org/W3010969086","https://openalex.org/W3036703963","https://openalex.org/W3043433718","https://openalex.org/W3125012172","https://openalex.org/W3152501898","https://openalex.org/W3154448381","https://openalex.org/W3155243801","https://openalex.org/W3158783012","https://openalex.org/W3166863226","https://openalex.org/W3167215031","https://openalex.org/W3167625290","https://openalex.org/W4200184446","https://openalex.org/W4205803619","https://openalex.org/W4240329257","https://openalex.org/W4289401659","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"Recommendation":[0],"systems":[1],"are":[2],"of":[3,9,44],"crucial":[4],"importance":[5],"for":[6],"a":[7,41],"variety":[8],"modern":[10,29],"apps":[11],"and":[12],"web":[13],"services,":[14],"such":[15,64],"as":[16],"news":[17],"feeds,":[18],"social":[19],"networks,":[20],"e-commerce,":[21],"search,":[22],"etc.":[23],"To":[24],"achieve":[25],"peak":[26],"prediction":[27],"accuracy,":[28],"recommendation":[30],"models":[31],"combine":[32],"deep":[33],"learning":[34],"with":[35],"terabyte-scale":[36],"embedding":[37],"tables":[38],"to":[39,57],"obtain":[40],"fine-grained":[42],"representation":[43],"the":[45,54],"underlying":[46],"data.":[47],"Traditional":[48],"inference":[49],"serving":[50],"architectures":[51],"require":[52],"deploying":[53],"whole":[55],"model":[56],"standalone":[58],"servers,":[59],"which":[60],"is":[61],"infeasible":[62],"at":[63],"massive":[65],"scale.":[66]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}