{"id":"https://openalex.org/W4400909497","doi":"https://doi.org/10.1109/icde60146.2024.00391","title":"GaussML: An End-to-End In-Database Machine Learning System","display_name":"GaussML: An End-to-End In-Database Machine Learning System","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4400909497","doi":"https://doi.org/10.1109/icde60146.2024.00391"},"language":"en","primary_location":{"id":"doi:10.1109/icde60146.2024.00391","doi":"https://doi.org/10.1109/icde60146.2024.00391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00391","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5119268361","display_name":"Guoliang Li","orcid":"https://orcid.org/0009-0007-8430-5141","observed_orcids":["https://orcid.org/0009-0007-8430-5141"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101225680","display_name":"Ji Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Sun","raw_affiliation_strings":["Huawei Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103731665","display_name":"Lijie Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Lijie Xu","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065134902","display_name":"Shifu Li","orcid":"https://orcid.org/0000-0003-3323-3276","observed_orcids":["https://orcid.org/0000-0003-3323-3276"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shifu Li","raw_affiliation_strings":["Huawei Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592887","display_name":"Jiang Wang","orcid":"https://orcid.org/0009-0007-5234-0516","observed_orcids":["https://orcid.org/0009-0007-5234-0516"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Wang","raw_affiliation_strings":["Huawei Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Company","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Wen Nie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Nie","raw_affiliation_strings":["Huawei Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Company","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3846,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83655683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5198","last_page":"5210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9907000064849854,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9907000064849854,"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/T11106","display_name":"Data Management and Algorithms","score":0.004800000227987766,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.00039999998989515007,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/in-database-machine-learning","display_name":"in-database machine learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/cardinality-estimation","display_name":"cardinality estimation","score":0.7379999756813049},{"id":"https://openalex.org/keywords/cost-estimation","display_name":"cost estimation","score":0.8960000276565552},{"id":"https://openalex.org/keywords/simd-acceleration","display_name":"SIMD acceleration","score":0.9789999723434448},{"id":"https://openalex.org/keywords/data-prefetching","display_name":"data prefetching","score":0.9890000224113464},{"id":"https://openalex.org/keywords/data-privacy","display_name":"data privacy","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7845114469528198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431066036224365},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.5404736399650574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4017341136932373},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3865547180175781},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22346296906471252}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde60146.2024.00391","doi":"https://doi.org/10.1109/icde60146.2024.00391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde60146.2024.00391","pdf_url":null,"source":{"id":"https://openalex.org/S4210210321","display_name":"IEEE International Conference on Data Engineering (ICDE)","issn_l":"1084-4627","issn":["1084-4627","2375-0286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5692501784","display_name":null,"funder_award_id":"61925205,62232009,62102215","funder_id":"https://openalex.org/F4320321002","funder_display_name":"Research Promotion Foundation"}],"funders":[{"id":"https://openalex.org/F4320321002","display_name":"Research Promotion Foundation","ror":"https://ror.org/00en9ce74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1987034518","https://openalex.org/W2003986132","https://openalex.org/W2036971997","https://openalex.org/W2044849727","https://openalex.org/W2060393849","https://openalex.org/W2090850279","https://openalex.org/W2127941149","https://openalex.org/W2168231600","https://openalex.org/W2181616869","https://openalex.org/W2184623761","https://openalex.org/W2396309311","https://openalex.org/W2402007731","https://openalex.org/W2402144811","https://openalex.org/W2510579098","https://openalex.org/W2553303224","https://openalex.org/W2613597870","https://openalex.org/W2750620035","https://openalex.org/W2780624097","https://openalex.org/W2786278116","https://openalex.org/W2941345940","https://openalex.org/W2944786596","https://openalex.org/W2948447697","https://openalex.org/W2949015162","https://openalex.org/W2963815651","https://openalex.org/W2970971581","https://openalex.org/W2991530444","https://openalex.org/W2997591727","https://openalex.org/W2998993395","https://openalex.org/W3002707609","https://openalex.org/W3085634762","https://openalex.org/W3127018844","https://openalex.org/W3185616770","https://openalex.org/W4240301789","https://openalex.org/W4281810104"],"related_works":["https://openalex.org/W4405721311","https://openalex.org/W4413360540","https://openalex.org/W4386768617","https://openalex.org/W3029900615","https://openalex.org/W2989078842","https://openalex.org/W7160944162","https://openalex.org/W7039188723","https://openalex.org/W2970216037","https://openalex.org/W4284964210","https://openalex.org/W4399208705"],"abstract_inverted_index":{"In-database":[0],"machine":[1,27,91],"learning":[2,28,92],"(In-DB":[3],"ML)":[4],"is":[5,37],"appealing":[6],"to":[7,24,33,49,134,152,172],"database":[8,23],"users":[9],"with":[10,62,102],"security":[11,60],"and":[12,54,65,75,131,148],"privacy":[13],"concerns,":[14],"as":[15,70],"it":[16],"avoids":[17],"copying":[18],"data":[19,73,149],"out":[20],"of":[21,78,164],"the":[22,38,43,51,120,136,154,173],"a":[25,88,162],"separate":[26],"system.":[29],"The":[30],"common":[31],"way":[32],"implement":[34,50],"in-DB":[35,175],"ML":[36,52,108,117,155,176],"ML-as-UDF":[39],"approach,":[40],"which":[41,96],"utilizes":[42],"User-Defined":[44],"Functions":[45],"(UDFs)":[46],"within":[47,110],"SQL":[48,79,104,111],"training":[53],"prediction.":[55],"However,":[56],"UDFs":[57],"may":[58],"introduce":[59],"risks":[61],"vulnerable":[63],"code,":[64],"suffer":[66],"from":[67],"performance":[68],"problems,":[69],"constrained":[71],"by":[72],"access":[74],"execution":[76],"patterns":[77],"query":[80,121,138],"operators.":[81],"To":[82,106],"address":[83],"these":[84],"limitations,":[85],"we":[86],"propose":[87],"new":[89],"in-database":[90],"system,":[93],"namely":[94],"GaussML,":[95],"provides":[97],"an":[98,128],"end-to-end":[99],"machine-learning":[100],"ability":[101],"native":[103],"interface.":[105],"support":[107],"training/inference":[109],"query,":[112],"GaussML":[113,125,141,167,182],"directly":[114],"integrates":[115],"typical":[116],"operators":[118,156],"into":[119],"engine":[122],"without":[123],"UDFs.":[124],"also":[126],"introduces":[127],"ML-aware":[129],"cardinality":[130],"cost":[132],"estimator":[133],"optimize":[135],"SQL+ML":[137],"plan.":[139],"Moreover,":[140],"leverages":[142],"Single":[143],"Instruction":[144],"Multiple":[145],"Data":[146],"(SIMD)":[147],"prefetching":[150],"techniques":[151],"accelerate":[153],"for":[157],"training.":[158],"We":[159],"have":[160],"implemented":[161],"series":[163],"algorithms":[165],"inside":[166],"in":[168,186],"openGauss":[169],"database.":[170],"Compared":[171],"state-of-the-art":[174],"systems":[177],"like":[178],"Apache":[179],"MADlib,":[180],"our":[181],"achieves":[183],"2-6\u00d7":[184],"speed-up":[185],"extensive":[187],"experiments.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-07-24T00:00:00"}