{"id":"https://openalex.org/W2988666181","doi":"https://doi.org/10.1109/cluster.2019.8890990","title":"HarpGBDT: Optimizing Gradient Boosting Decision Tree for Parallel Efficiency","display_name":"HarpGBDT: Optimizing Gradient Boosting Decision Tree for Parallel Efficiency","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2988666181","doi":"https://doi.org/10.1109/cluster.2019.8890990","mag":"2988666181"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2019.8890990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5101652188","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0002-1183-9165"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108081911","display_name":"Judy Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Judy Qiu","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102735620","display_name":"Langshi Chen","orcid":"https://orcid.org/0009-0005-4800-3782"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Langshi Chen","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435411","display_name":"Jiayu Li","orcid":"https://orcid.org/0000-0002-9789-1908"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayu Li","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082534206","display_name":"Miao Jiang","orcid":"https://orcid.org/0000-0001-7128-8943"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miao Jiang","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082430061","display_name":"Selahattin Akkas","orcid":"https://orcid.org/0000-0001-8121-9300"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Selahattin Akkas","raw_affiliation_strings":["Indiana University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025108845","display_name":"Egor Smirnov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Egor Smirnov","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033108881","display_name":"Ruslan Israfilov","orcid":"https://orcid.org/0000-0002-4226-9644"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruslan Israfilov","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084207579","display_name":"Sergey Khekhnev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sergey Khekhnev","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045841184","display_name":"A. V. Nikolaev","orcid":"https://orcid.org/0000-0002-1225-2673"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrey Nikolaev","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3051,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.61927032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9987000226974487,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9976000189781189,"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":0.8816617727279663},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6671625375747681},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.49811506271362305},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46519243717193604},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4643687605857849},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.44758573174476624},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.42146554589271545},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4146590232849121},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4103856384754181},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32577019929885864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30397891998291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816617727279663},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6671625375747681},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.49811506271362305},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46519243717193604},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4643687605857849},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.44758573174476624},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.42146554589271545},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4146590232849121},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4103856384754181},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32577019929885864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30397891998291016},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2019.8890990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2019.8890990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1483135265","https://openalex.org/W1489069776","https://openalex.org/W1598873931","https://openalex.org/W1678356000","https://openalex.org/W1987356990","https://openalex.org/W2012290523","https://openalex.org/W2024046085","https://openalex.org/W2060393849","https://openalex.org/W2076618162","https://openalex.org/W2083842231","https://openalex.org/W2106100548","https://openalex.org/W2125816831","https://openalex.org/W2292355502","https://openalex.org/W2295598076","https://openalex.org/W2553372643","https://openalex.org/W2586297576","https://openalex.org/W2592340788","https://openalex.org/W2652074165","https://openalex.org/W2740731087","https://openalex.org/W2747420241","https://openalex.org/W2751051839","https://openalex.org/W2768348081","https://openalex.org/W2783448383","https://openalex.org/W2799138232","https://openalex.org/W2803583343","https://openalex.org/W2886958107","https://openalex.org/W2898227265","https://openalex.org/W2911964244","https://openalex.org/W2952714963","https://openalex.org/W3102476541","https://openalex.org/W4407741721","https://openalex.org/W6628845210","https://openalex.org/W6637322457","https://openalex.org/W6665801690","https://openalex.org/W6729681907","https://openalex.org/W6739629539","https://openalex.org/W6741642434","https://openalex.org/W6745609711","https://openalex.org/W6751815881","https://openalex.org/W6755712434"],"related_works":["https://openalex.org/W2505067803","https://openalex.org/W1634740951","https://openalex.org/W2542593149","https://openalex.org/W2148563915","https://openalex.org/W2125652721","https://openalex.org/W2286735113","https://openalex.org/W3108206494","https://openalex.org/W2739726746","https://openalex.org/W4242380336","https://openalex.org/W2389274008"],"abstract_inverted_index":{"Gradient":[0],"Boosting":[1],"Decision":[2],"Tree":[3],"(GBDT)":[4],"is":[5,23,53,60,77,186],"a":[6,33,82,97,138,142,156,164],"widely":[7],"used":[8],"machine":[9],"learning":[10],"algorithm,":[11],"whose":[12],"training":[13,129],"involves":[14],"both":[15],"irregular":[16],"computation":[17],"and":[18,22,42,56,131,136,182,217],"random":[19,74],"memory":[20,75],"access":[21],"challenging":[24],"for":[25,50],"system":[26,85],"optimizations.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,95,126,154],"conduct":[32],"comprehensive":[34],"performance":[35],"analysis":[36],"of":[37,73,90,108,115,118,149,163,167,172,178],"two":[38,46],"state-of-the-art":[39],"systems,":[40],"XGBoost":[41,216],"LightGBM.":[43,221],"They":[44],"represent":[45],"typical":[47],"parallel":[48,55,61,91,183,191],"implementations":[49],"GBDT;":[51],"one":[52,59],"data":[54,130,133],"the":[57,71,88,104,113,122,128,147,161,176,179,204],"other":[58],"over":[62],"features.":[63],"Substantial":[64],"thread":[65],"synchronization":[66],"overhead,":[67],"as":[68,70,141],"well":[69],"inefficiency":[72],"access,":[76],"identified.":[78],"We":[79],"propose":[80,137,155],"HarpGBDT,":[81],"new":[83,98],"GBDT":[84],"designed":[86],"from":[87],"perspective":[89],"efficiency":[92],"optimization.":[93],"Firstly,":[94],"adopt":[96],"tree":[99,109],"growth":[100],"method":[101],"that":[102,145],"selects":[103],"top":[105],"K":[106],"candidates":[107],"nodes":[110],"to":[111,159,188],"enable":[112],"use":[114],"more":[116],"levels":[117],"parallelism":[119,151,168],"without":[120],"sacrificing":[121],"algorithm's":[123],"accuracy.":[124],"Secondly,":[125],"organize":[127],"model":[132,144],"in":[134,169],"blocks":[135],"block-wise":[139],"approach":[140],"general":[143],"enables":[146],"exploration":[148],"various":[150],"options.":[152],"Thirdly,":[153],"mixed":[157],"mode":[158,166],"utilize":[160],"advantages":[162],"different":[165,170,200],"phases":[171],"training.":[173],"By":[174,193],"changing":[175],"configuration":[177],"block":[180],"size":[181],"mode,":[184],"HarpGBDT":[185,209],"able":[187],"attain":[189],"better":[190],"efficiency.":[192],"extensive":[194],"experiments":[195],"on":[196,203,210],"four":[197],"datasets":[198],"with":[199],"statistical":[201],"characteristics":[202],"Intel(R)":[205],"Xeon(R)":[206],"E5-2699":[207],"server,":[208],"average":[211],"performs":[212],"8x":[213],"faster":[214,219],"than":[215,220],"2.6x":[218]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}