{"id":"https://openalex.org/W4380668113","doi":"https://doi.org/10.1145/3592980.3595318","title":"Random Forests over normalized data in CPU-GPU DBMSes","display_name":"Random Forests over normalized data in CPU-GPU DBMSes","publication_year":2023,"publication_date":"2023-06-14","ids":{"openalex":"https://openalex.org/W4380668113","doi":"https://doi.org/10.1145/3592980.3595318"},"language":"en","primary_location":{"id":"doi:10.1145/3592980.3595318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592980.3595318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002877429","display_name":"Zezhou Huang","orcid":"https://orcid.org/0009-0002-6613-0337"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zezhou Huang","raw_affiliation_strings":["Columbia University, US"],"raw_orcid":"https://orcid.org/0009-0002-6613-0337","affiliations":[{"raw_affiliation_string":"Columbia University, US","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092169229","display_name":"Pavan Kalyan Damalapati","orcid":"https://orcid.org/0009-0009-2825-0793"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Kalyan Damalapati","raw_affiliation_strings":["Columbia University, US"],"raw_orcid":"https://orcid.org/0009-0009-2825-0793","affiliations":[{"raw_affiliation_string":"Columbia University, US","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061137265","display_name":"Rathijit Sen","orcid":"https://orcid.org/0000-0003-4736-2837"},"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":"Rathijit Sen","raw_affiliation_strings":["Microsoft, US"],"raw_orcid":"https://orcid.org/0000-0003-4736-2837","affiliations":[{"raw_affiliation_string":"Microsoft, US","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, US"],"raw_orcid":"https://orcid.org/0000-0003-4254-6688","affiliations":[{"raw_affiliation_string":"Columbia University, US","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"98","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9948999881744385,"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/T10320","display_name":"Neural Networks and Applications","score":0.9902999997138977,"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":0.8748918175697327},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7581359148025513},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6480159759521484},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6409831047058105},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.561122715473175},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5260536670684814},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4402267336845398},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4277825653553009},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25459855794906616},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21202018857002258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20496174693107605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748918175697327},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7581359148025513},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6480159759521484},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6409831047058105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.561122715473175},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5260536670684814},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4402267336845398},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4277825653553009},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25459855794906616},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21202018857002258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20496174693107605}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3592980.3595318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3592980.3595318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Workshop on Data Management on New Hardware","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.699999988079071,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1578512165","https://openalex.org/W2012449229","https://openalex.org/W2295598076","https://openalex.org/W2399715892","https://openalex.org/W2948085204","https://openalex.org/W2949054050","https://openalex.org/W2953564033","https://openalex.org/W2962991166","https://openalex.org/W3032789239","https://openalex.org/W3046551054","https://openalex.org/W4205803619","https://openalex.org/W4241185933","https://openalex.org/W4254018622","https://openalex.org/W4295695956","https://openalex.org/W4312559100","https://openalex.org/W4386123448","https://openalex.org/W6969259846"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W2257409849","https://openalex.org/W2033526630"],"abstract_inverted_index":{"This":[0],"short":[1],"paper":[2],"studies":[3],"query":[4,26],"execution":[5,27],"based":[6],"on":[7,10,73],"message":[8,40],"passing":[9,41],"CPU-GPU":[11,54],"systems,":[12],"using":[13,39,60],"random":[14,57],"forests":[15],"training":[16,36,56],"as":[17],"the":[18,32,65],"workload.":[19],"We":[20,46],"investigate":[21],"different":[22,43],"data":[23,51],"placement":[24,52],"and":[25,29,53],"strategies":[28],"find":[30],"that":[31,48],"unique":[33],"properties":[34],"of":[35],"ML":[37,68],"models":[38,59],"necessitates":[42],"design":[44],"decisions.":[45],"show":[47],"with":[49],"proper":[50],"co-execution,":[55],"forest":[58],"pure":[61],"SQL":[62],"can":[63],"outperform":[64],"leading":[66],"LightGBM":[67],"library":[69],"by":[70],"1.5":[71],"\u00d7":[72],"SSB":[74],"SF=10.":[75]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}