{"id":"https://openalex.org/W4401863505","doi":"https://doi.org/10.1145/3637528.3671964","title":"Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs","display_name":"Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863505","doi":"https://doi.org/10.1145/3637528.3671964"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5103116142","display_name":"Jiahuan Yan","orcid":"https://orcid.org/0000-0002-2002-2579"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahuan Yan","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2002-2579","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023258354","display_name":"Jintai Chen","orcid":"https://orcid.org/0000-0002-3199-2597"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jintai Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3199-2597","affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianxing Wang","orcid":"https://orcid.org/0009-0001-0193-6164"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxing Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0193-6164","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060901632","display_name":"Danny Z. Chen","orcid":"https://orcid.org/0000-0001-6565-2884"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danny Z. Chen","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6565-2884","affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071068569","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3230-6392"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3230-6392","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3679","last_page":"3689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9962000250816345,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9936000108718872,"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/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6724161505699158},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.610883355140686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.444724440574646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44210341572761536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12284108996391296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6724161505699158},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.610883355140686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.444724440574646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44210341572761536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12284108996391296},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1559060276","https://openalex.org/W1985258161","https://openalex.org/W2023320048","https://openalex.org/W2076618162","https://openalex.org/W2125621954","https://openalex.org/W2295598076","https://openalex.org/W2512971201","https://openalex.org/W2749348810","https://openalex.org/W2898085636","https://openalex.org/W2979691890","https://openalex.org/W2997591727","https://openalex.org/W3006436762","https://openalex.org/W3015609966","https://openalex.org/W3098350627","https://openalex.org/W3101704389","https://openalex.org/W3174086521","https://openalex.org/W3200947677","https://openalex.org/W3202428668","https://openalex.org/W3216660278","https://openalex.org/W4200630877","https://openalex.org/W4281260498","https://openalex.org/W4292779060","https://openalex.org/W4385565006","https://openalex.org/W4390889742","https://openalex.org/W6775706467","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Tabular":[0],"datasets":[1],"play":[2],"a":[3,53,73,87,120,127,175,183,190,198,204],"crucial":[4],"role":[5],"in":[6,86,112,222],"various":[7],"applications.":[8],"Thus,":[9],"developing":[10],"efficient,":[11],"effective,":[12],"and":[13,33,83,96,156,220,236,243],"widely":[14],"compatible":[15],"prediction":[16,45],"algorithms":[17],"for":[18,52,104],"tabular":[19,44,55,166,225],"data":[20],"is":[21,57,91,97,110,214],"important.":[22],"Currently,":[23],"two":[24],"prominent":[25],"model":[26,51,67,157,234],"types,":[27],"Gradient":[28],"Boosted":[29],"Decision":[30],"Trees":[31],"(GBDTs)":[32],"Deep":[34],"Neural":[35],"Networks":[36],"(DNNs),":[37],"have":[38,159],"demonstrated":[39],"performance":[40],"advantages":[41,79],"on":[42],"distinct":[43],"tasks.":[46],"However,":[47],"selecting":[48],"an":[49,113],"effective":[50,99],"specific":[54],"dataset":[56,102],"challenging,":[58],"often":[59],"demanding":[60],"time-consuming":[61],"hyperparameter":[62],"tuning.":[63],"To":[64],"address":[65],"this":[66,70],"selection":[68],"dilemma,":[69],"paper":[71],"proposes":[72],"new":[74],"framework":[75],"that":[76,90,115,124,212],"amalgamates":[77],"the":[78,132,144],"of":[80,101],"both":[81],"GBDTs":[82,95,105,221],"DNNs,":[84],"resulting":[85],"DNN":[88,191],"algorithm":[89],"as":[92,94,195,197],"efficient":[93],"competitively":[98],"regardless":[100],"preferences":[103],"or":[106],"DNNs.":[107],"Our":[108],"idea":[109],"rooted":[111],"observation":[114],"deep":[116],"learning":[117],"(DL)":[118],"offers":[119],"larger":[121],"parameter":[122],"space":[123],"can":[125],"represent":[126],"well-performing":[128],"GBDT":[129,148,187],"model,":[130],"yet":[131],"current":[133],"back-propagation":[134,200],"optimizer":[135,201],"struggles":[136],"to":[137,161,165],"efficiently":[138],"discover":[139],"such":[140],"optimal":[141],"functionality.":[142],"On":[143],"other":[145],"hand,":[146],"during":[147],"development,":[149],"hard":[150],"tree":[151],"pruning,":[152],"entropy-driven":[153],"feature":[154,188],"gate,":[155,189],"ensemble":[158],"proved":[160],"be":[162],"more":[163],"adaptable":[164],"data.":[167],"By":[168],"combining":[169],"these":[170],"key":[171],"components,":[172],"we":[173],"present":[174],"Tree-hybrid":[176],"simple":[177],"MLP":[178,207],"(T-MLP).":[179],"In":[180],"our":[181],"framework,":[182],"tensorized,":[184],"rapidly":[185],"trained":[186],"architecture":[192],"pruning":[193],"approach,":[194],"well":[196],"vanilla":[199],"collaboratively":[202],"train":[203],"randomly":[205],"initialized":[206],"model.":[208],"Comprehensive":[209],"experiments":[210],"show":[211],"T-MLP":[213],"competitive":[215],"with":[216,232],"extensively":[217],"tuned":[218],"DNNs":[219],"their":[223],"dominating":[224],"benchmarks":[226],"(88":[227],"datasets)":[228],"respectively,":[229],"all":[230],"achieved":[231],"compact":[233],"storage":[235],"significantly":[237],"reduced":[238],"training":[239],"duration.":[240],"The":[241],"codes":[242],"full":[244],"experiment":[245],"results":[246],"are":[247],"available":[248],"at":[249],"https://github.com/jyansir/tmlp.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}