{"id":"https://openalex.org/W2936191805","doi":"https://doi.org/10.1007/s10994-020-05888-2","title":"Bonsai: diverse and shallow trees for extreme multi-label classification","display_name":"Bonsai: diverse and shallow trees for extreme multi-label classification","publication_year":2020,"publication_date":"2020-08-23","ids":{"openalex":"https://openalex.org/W2936191805","doi":"https://doi.org/10.1007/s10994-020-05888-2","mag":"2936191805"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-020-05888-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05888-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05888-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05888-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013829850","display_name":"Sujay Khandagale","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sujay Khandagale","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631160","display_name":"Han Xiao","orcid":"https://orcid.org/0000-0002-3548-3204"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Han Xiao","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102987303","display_name":"Rohit Babbar","orcid":"https://orcid.org/0000-0002-3787-8971"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Rohit Babbar","raw_affiliation_strings":["Aalto University, Helsinki, Finland","Aalto University Helsinki, Finland#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-3787-8971","affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.7603,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87750024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"109","issue":"11","first_page":"2099","last_page":"2119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.968999981880188,"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/suite","display_name":"Suite","score":0.7243019938468933},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7018729448318481},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6672427654266357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6206047534942627},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5898579955101013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48578742146492004},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4851608872413635},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4237639904022217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37684887647628784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37289339303970337},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3393714129924774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33072447776794434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2674068808555603},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13246411085128784},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10787352919578552}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7243019938468933},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7018729448318481},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6672427654266357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206047534942627},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5898579955101013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48578742146492004},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4851608872413635},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4237639904022217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37684887647628784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37289339303970337},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3393714129924774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33072447776794434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2674068808555603},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13246411085128784},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10787352919578552},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-020-05888-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05888-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05888-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1904.08249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08249","pdf_url":"https://arxiv.org/pdf/1904.08249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:2936191805","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1904.08249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.08249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.08249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10994-020-05888-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-020-05888-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-020-05888-2.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2936191805.pdf","grobid_xml":"https://content.openalex.org/works/W2936191805.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W193151672","https://openalex.org/W756166754","https://openalex.org/W1832693441","https://openalex.org/W1834987204","https://openalex.org/W1940008012","https://openalex.org/W1959000896","https://openalex.org/W1967542092","https://openalex.org/W1987549167","https://openalex.org/W1995341420","https://openalex.org/W2027869746","https://openalex.org/W2061873838","https://openalex.org/W2063270776","https://openalex.org/W2068074736","https://openalex.org/W2114393161","https://openalex.org/W2118585731","https://openalex.org/W2123217057","https://openalex.org/W2145827727","https://openalex.org/W2146241755","https://openalex.org/W2150593711","https://openalex.org/W2153579005","https://openalex.org/W2155144632","https://openalex.org/W2163605009","https://openalex.org/W2183087644","https://openalex.org/W2359108789","https://openalex.org/W2362855512","https://openalex.org/W2437817353","https://openalex.org/W2461743311","https://openalex.org/W2515754823","https://openalex.org/W2520348554","https://openalex.org/W2739996966","https://openalex.org/W2740731087","https://openalex.org/W2743021690","https://openalex.org/W2744136723","https://openalex.org/W2767245172","https://openalex.org/W2788125153","https://openalex.org/W2808417254","https://openalex.org/W2890634844","https://openalex.org/W2898830107","https://openalex.org/W2921113176","https://openalex.org/W2944514791","https://openalex.org/W2945136801","https://openalex.org/W2945879563","https://openalex.org/W2947795521","https://openalex.org/W2963626623","https://openalex.org/W2966704088","https://openalex.org/W4299911419","https://openalex.org/W6677656871","https://openalex.org/W6682939927","https://openalex.org/W6764172607"],"related_works":["https://openalex.org/W2788125153","https://openalex.org/W2744136723","https://openalex.org/W2743021690","https://openalex.org/W2520348554","https://openalex.org/W2461743311","https://openalex.org/W2921113176","https://openalex.org/W2739996966","https://openalex.org/W2362855512","https://openalex.org/W2068074736","https://openalex.org/W756166754","https://openalex.org/W2965373594","https://openalex.org/W2963341956","https://openalex.org/W2906963924","https://openalex.org/W1940008012","https://openalex.org/W2181610118","https://openalex.org/W2955304269","https://openalex.org/W82431984","https://openalex.org/W2509476293","https://openalex.org/W3094110505","https://openalex.org/W2751260683"],"abstract_inverted_index":{"Abstract":[0],"Extreme":[1],"multi-label":[2,10],"classification":[3],"(":[4],"XMC":[5],")":[6],"refers":[7],"to":[8,49,113,137,176],"supervised":[9],"learning":[11],"involving":[12],"hundreds":[13],"of":[14,19,28,36,58,120,130,167],"thousands":[15],"or":[16],"even":[17],"millions":[18],"labels.":[20],"In":[21],"this":[22,59],"paper,":[23],"we":[24],"develop":[25],"a":[26,152,161],"suite":[27],"algorithms,":[29],"called":[30],",":[31],"which":[32,68,134],"generalizes":[33],"the":[34,43,46,65,72,76,92,97,103,118,128],"notion":[35],"label":[37,60,81,125],"representation":[38,47,61],"in":[39,45,109,141,165],"XMC,":[40,142],"and":[41,90,99,123,143],"partitions":[42,106],"labels":[44],"space":[48,62,67,78,94],"learn":[50],"shallow":[51,114,121],"trees.":[52,115],"We":[53],"show":[54],"three":[55],"concrete":[56],"realizations":[57],"including:":[63],"(i)":[64],"input":[66,73,98],"is":[69,135,181],"spanned":[70,79],"by":[71,80,95],"features,":[74],"(ii)":[75],"output":[77,100],"vectors":[82],"based":[83],"on":[84,149],"their":[85],"co-occurrence":[86],"with":[87,156],"other":[88],"labels,":[89,159],"(iii)":[91],"joint":[93],"combining":[96,117],"representations.":[101],"Furthermore,":[102],"constraint-free":[104],"multi-way":[105],"learnt":[107],"iteratively":[108],"these":[110],"spaces":[111],"lead":[112],"By":[116],"effect":[119],"trees":[122],"generalized":[124],"representation,":[126],"achieves":[127],"best":[129],"both":[131],"worlds\u2014fast":[132],"training":[133],"comparable":[136],"state-of-the-art":[138,162],"tree-based":[139],"methods":[140],"much":[144],"better":[145],"prediction":[146,168],"accuracy,":[147,169],"particularly":[148],"tail-labels.":[150],"On":[151],"benchmark":[153],"Amazon-3M":[154],"dataset":[155],"3":[157],"million":[158],"outperforms":[160],"one-vs-rest":[163],"method":[164],"terms":[166],"while":[170],"being":[171],"approximately":[172],"200":[173],"times":[174],"faster":[175],"train.":[177],"The":[178],"code":[179],"for":[180],"available":[182],"at":[183],"https://github.com/xmc-aalto/bonsai":[184],".":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}