{"id":"https://openalex.org/W2890634844","doi":"https://doi.org/10.48550/arxiv.1810.11671","title":"A no-regret generalization of hierarchical softmax to extreme multi-label classification","display_name":"A no-regret generalization of hierarchical softmax to extreme multi-label classification","publication_year":2018,"publication_date":"2018-10-27","ids":{"openalex":"https://openalex.org/W2890634844","doi":"https://doi.org/10.48550/arxiv.1810.11671","mag":"2890634844"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1810.11671","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.11671","pdf_url":"https://arxiv.org/pdf/1810.11671","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1810.11671","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079988726","display_name":"Marek Wydmuch","orcid":"https://orcid.org/0000-0002-6598-6304","observed_orcids":["https://orcid.org/0000-0002-6598-6304"]},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["BE","PL"],"is_corresponding":false,"raw_author_name":"Wydmuch, Marek","raw_affiliation_strings":["Institute of Computing Science Poznan University of Technology , Poland","Ghent University, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science Poznan University of Technology , Poland","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Ghent University, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014040333","display_name":"Kalina Jasinska-Kobus","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jasinska, Kalina","raw_affiliation_strings":["Institute of Computing Science Poznan University of Technology , Poland","Pozna\u0144 University of Technology, Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Science Poznan University of Technology , Poland","institution_ids":["https://openalex.org/I46597724"]},{"raw_affiliation_string":"Pozna\u0144 University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060635553","display_name":"Mikhail Kuznetsov","orcid":"https://orcid.org/0000-0003-1009-7224","observed_orcids":["https://orcid.org/0000-0003-1009-7224"]},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Kuznetsov, Mikhail","raw_affiliation_strings":["Yahoo! Research New York , USA","Moscow Institute of Physics and Technology, Dolgoprudnyy, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research New York , USA","institution_ids":[]},{"raw_affiliation_string":"Moscow Institute of Physics and Technology, Dolgoprudnyy, Russia","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047520070","display_name":"R\u00f3bert Busa\u2010Fekete","orcid":"https://orcid.org/0000-0002-3691-650X","observed_orcids":["https://orcid.org/0000-0002-3691-650X"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Busa-Fekete, R\u00f3bert","raw_affiliation_strings":["Yahoo! Research New York , USA","Google (United States), Mountain View, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research New York , USA","institution_ids":[]},{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080799924","display_name":"Krzysztof Dembczy\u0144ski","orcid":"https://orcid.org/0000-0001-7477-6758","observed_orcids":["https://orcid.org/0000-0001-7477-6758"]},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dembczy\u0144ski, Krzysztof","raw_affiliation_strings":["Pozna\u0144 University of Technology, Poznan, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pozna\u0144 University of Technology, Poznan, Poland","institution_ids":["https://openalex.org/I46597724"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"6355","last_page":"6366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.98580002784729,"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":0.98580002784729,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0032999999821186066,"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/T10028","display_name":"Topic Modeling","score":0.0027000000700354576,"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/extreme-multi-label-classification","display_name":"extreme multi-label classification","score":0.9940000176429749},{"id":"https://openalex.org/keywords/no-regret-learning","display_name":"no-regret learning","score":0.8539999723434448},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.44699999690055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764678597450256},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6904396414756775},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6401779651641846},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.595792293548584},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5880745649337769},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5758190751075745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652856230735779},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5567610859870911},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5211268067359924},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.508293092250824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.507379949092865},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43279415369033813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33617058396339417},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25955432653427124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1131691038608551},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1810.11671","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.11671","pdf_url":"https://arxiv.org/pdf/1810.11671","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.1810.11671","doi":"https://doi.org/10.48550/arxiv.1810.11671","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1810.11671","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2890634844","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1810.11671.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1810.11671","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1810.11671","pdf_url":"https://arxiv.org/pdf/1810.11671","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890634844.pdf","grobid_xml":"https://content.openalex.org/works/W2890634844.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1723811852","https://openalex.org/W2468328197"],"related_works":["https://openalex.org/W3088109833","https://openalex.org/W4404650033","https://openalex.org/W2941950312","https://openalex.org/W4306317628","https://openalex.org/W7203664559","https://openalex.org/W3135980569","https://openalex.org/W2995855391","https://openalex.org/W4404396553","https://openalex.org/W4409149246","https://openalex.org/W2970574105"],"abstract_inverted_index":{"Extreme":[0],"multi-label":[1,77,101],"classification":[2],"(XMLC)":[3],"is":[4,83,105,112,152],"a":[5,12,38,75,86,97,142],"problem":[6],"of":[7,15,24,79,123,160],"tagging":[8],"an":[9,20,175],"instance":[10],"with":[11,109,136],"small":[13],"subset":[14],"relevant":[16],"labels":[17,36],"chosen":[18],"from":[19,100],"extremely":[21],"large":[22],"pool":[23],"possible":[25],"labels.":[26],"Large":[27],"label":[28,58],"spaces":[29],"can":[30],"be":[31],"efficiently":[32],"handled":[33],"by":[34],"organizing":[35],"as":[37,85,127],"tree,":[39],"like":[40],"in":[41,115,158,174],"the":[42,137],"hierarchical":[43],"softmax":[44],"(HSM)":[45],"approach":[46],"commonly":[47],"used":[48,84,107],"for":[49,66,147],"multi-class":[50,103],"problems.":[51,69,149],"In":[52],"this":[53],"paper,":[54],"we":[55,91],"investigate":[56],"probabilistic":[57],"trees":[59],"(PLTs)":[60],"that":[61,72,93,104,120],"have":[62],"been":[63],"recently":[64],"devised":[65],"tackling":[67],"XMLC":[68,148],"We":[70,117],"show":[71,119],"PLTs":[73],"are":[74],"no-regret":[76],"generalization":[78],"HSM":[80,110,135],"when":[81],"precision@k":[82],"model":[87,163],"evaluation":[88],"metric.":[89],"Critically,":[90],"prove":[92],"pick-one-label":[94,138],"heuristic":[95,139],"-":[96,111],"reduction":[98],"technique":[99],"to":[102,126,154,172],"routinely":[106],"along":[108],"not":[113],"consistent":[114],"general.":[116],"also":[118],"our":[121],"implementation":[122],"PLTs,":[124],"referred":[125],"extremeText":[128],"(XT),":[129],"obtains":[130],"significantly":[131],"better":[132],"results":[133],"than":[134],"and":[140,165],"XML-CNN,":[141],"deep":[143],"network":[144],"specifically":[145],"designed":[146],"Moreover,":[150],"XT":[151],"competitive":[153],"many":[155],"state-of-the-art":[156],"approaches":[157],"terms":[159],"statistical":[161],"performance,":[162],"size":[164],"prediction":[166],"time":[167],"which":[168],"makes":[169],"it":[170],"amenable":[171],"deploy":[173],"online":[176],"system.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-09-27T00:00:00"}