{"id":"https://openalex.org/W4409149731","doi":"https://doi.org/10.1145/3690624.3709271","title":"ScalaGBM: Memory Efficient GBDT Training for High-Dimensional Data on GPU","display_name":"ScalaGBM: Memory Efficient GBDT Training for High-Dimensional Data on GPU","publication_year":2025,"publication_date":"2025-04-04","ids":{"openalex":"https://openalex.org/W4409149731","doi":"https://doi.org/10.1145/3690624.3709271"},"language":"en","primary_location":{"id":"doi:10.1145/3690624.3709271","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709271","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3690624.3709271","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113671741","display_name":"Borui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Borui Xu","raw_affiliation_strings":["Shandong University, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0001-8226-4661","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, Shandong, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013127195","display_name":"Zeyi Wen","orcid":"https://orcid.org/0000-0003-3370-6053"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeyi Wen","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China & Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3370-6053","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China & Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394256","display_name":"Yao Chen","orcid":"https://orcid.org/0000-0002-5798-2282"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yao Chen","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5798-2282","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045962522","display_name":"Weiguo Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Liu","raw_affiliation_strings":["Shandong University, Jinan, Shandong Province, China"],"raw_orcid":"https://orcid.org/0000-0001-8834-0453","affiliations":[{"raw_affiliation_string":"Shandong University, Jinan, Shandong Province, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4281-2053","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8618-4581","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1669","last_page":"1678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9904999732971191,"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":0.8294902443885803},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4891407787799835},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.47092074155807495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294902443885803},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4891407787799835},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.47092074155807495},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3690624.3709271","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709271","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-165769","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-165769","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3690624.3709271","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3690624.3709271","pdf_url":null,"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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W2112452856","https://openalex.org/W2128853364","https://openalex.org/W2295598076","https://openalex.org/W2509235963","https://openalex.org/W2604808181","https://openalex.org/W2614375709","https://openalex.org/W2799138232","https://openalex.org/W2886958107","https://openalex.org/W2906922093","https://openalex.org/W2911495555","https://openalex.org/W2912083425","https://openalex.org/W2912265134","https://openalex.org/W2947404296","https://openalex.org/W2948000013","https://openalex.org/W2950445386","https://openalex.org/W2954558120","https://openalex.org/W2955798121","https://openalex.org/W2963554098","https://openalex.org/W2997591727","https://openalex.org/W3035275162","https://openalex.org/W3124190522","https://openalex.org/W3191093003","https://openalex.org/W3195070922","https://openalex.org/W3216660278","https://openalex.org/W4205348240","https://openalex.org/W4205539948","https://openalex.org/W4206830372","https://openalex.org/W4206896921","https://openalex.org/W4206908526","https://openalex.org/W4210689632","https://openalex.org/W4213052788","https://openalex.org/W4309955312","https://openalex.org/W4321458190","https://openalex.org/W6614148910","https://openalex.org/W6758229760"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Gradient":[0],"Boosted":[1],"Decision":[2],"Trees":[3],"(GBDTs)":[4],"are":[5],"classical":[6],"machine":[7],"learning":[8],"algorithms":[9],"widely":[10,34],"employed":[11],"in":[12,25],"recommendation":[13],"systems,":[14],"database":[15],"queries,":[16],"etc.":[17],"Due":[18],"to":[19,36,51,78,98,118,140],"the":[20,38,53,100,104,110,120,125,143,191],"extensive":[21],"memory":[22,50,85,101,122],"access":[23],"involved":[24],"histogram-based":[26],"GBDT":[27,73,170,187],"training":[28,54,61,82,105,111,144,192],"methods,":[29],"high-bandwidth":[30],"GPUs":[31],"have":[32],"been":[33],"adopted":[35],"accelerate":[37,79],"training.":[39],"However,":[40],"when":[41],"handling":[42],"millions":[43],"of":[44,103,159,183],"feature":[45],"data,":[46],"it":[47],"requires":[48],"significant":[49],"store":[52],"data":[55,81,92],"and":[56,94,134],"histograms,":[57],"posing":[58],"challenges":[59],"for":[60,124],"on":[62],"limited":[63],"GPU":[64,167],"memories.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,108,128],"develop":[70,129],"a":[71,90,114,164,180],"GPU-based":[72],"framework":[74],"named":[75],"ScalaGBM,":[76],"aiming":[77],"high-dimensional":[80],"with":[83,113,154,163],"less":[84],"usage.":[86],"We":[87],"first":[88],"employ":[89],"CSR-like":[91],"format":[93],"CSR-based":[95],"histogram":[96,132],"construction":[97,133],"reduce":[99,119],"occupation":[102],"data.":[106],"Then,":[107],"reorganize":[109],"workflow":[112],"double":[115],"buffer":[116],"structure":[117],"overall":[121],"consumption":[123],"histogram.":[126],"Finally,":[127],"multi-dimensional":[130],"parallel":[131],"global":[135],"optimal":[136],"split":[137],"point":[138],"reduction":[139],"speed":[141],"up":[142],"process.":[145],"Experimental":[146],"results":[147],"demonstrate":[148],"that":[149],"ScalaGBM":[150,178],"handles":[151],"real-world":[152],"datasets":[153],"over":[155,185],"100":[156],"million":[157,161],"instances":[158],"50":[160],"features":[162],"single":[165],"commercial":[166],"while":[168],"existing":[169],"frameworks":[171],"all":[172],"run":[173],"into":[174],"out-of-memory":[175],"errors.":[176],"Meanwhile,":[177],"achieves":[179],"maximum":[181],"speedup":[182],"39\u00d7":[184],"state-of-the-art":[186],"counterparts":[188],"without":[189],"sacrificing":[190],"quality.":[193],"The":[194],"code":[195],"is":[196],"available":[197],"at":[198],"https://github.com/Xtra-Computing/thundergbm.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}