{"id":"https://openalex.org/W4306750934","doi":"https://doi.org/10.1007/s10994-022-06228-2","title":"Speeding-up one-versus-all training for extreme classification via mean-separating initialization","display_name":"Speeding-up one-versus-all training for extreme classification via mean-separating initialization","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4306750934","doi":"https://doi.org/10.1007/s10994-022-06228-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-022-06228-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06228-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06228-2.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06228-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070761496","display_name":"Erik Schultheis","orcid":"https://orcid.org/0000-0003-1685-8397"},"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":true,"raw_author_name":"Erik Schultheis","raw_affiliation_strings":["Department of Computer Science, Aalto University, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-1685-8397","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","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":["Department of Computer Science, Aalto University, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070761496"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":{"value":3290,"currency":"USD","value_usd":3290},"fwci":1.4675,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84905005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"111","issue":"11","first_page":"3953","last_page":"3976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9934999942779541,"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":0.9934999942779541,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9918000102043152,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9894999861717224,"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/initialization","display_name":"Initialization","score":0.8727370500564575},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8318533897399902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.643589437007904},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6285171508789062},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4929926097393036},{"id":"https://openalex.org/keywords/sequential-minimal-optimization","display_name":"Sequential minimal optimization","score":0.4767364263534546},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43290114402770996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4229137599468231},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.37981051206588745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3394920229911804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33206161856651306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3060970604419708},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08971437811851501}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8727370500564575},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8318533897399902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643589437007904},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6285171508789062},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4929926097393036},{"id":"https://openalex.org/C10719679","wikidata":"https://www.wikidata.org/wiki/Q2679145","display_name":"Sequential minimal optimization","level":3,"score":0.4767364263534546},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43290114402770996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4229137599468231},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.37981051206588745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3394920229911804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33206161856651306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3060970604419708},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08971437811851501},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-022-06228-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06228-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06228-2.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:aaltodoc.aalto.fi:123456789/117680","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/9ab2daf7-6046-472d-b987-28feff91b375","pdf_url":"https://research.aalto.fi/files/91141091/Speeding_up_one_versus_all_training_for_extreme_classification_via_mean_separating_initialization.pdf","source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10994-022-06228-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06228-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06228-2.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":[],"awards":[{"id":"https://openalex.org/G8559131367","display_name":"High Performance Computing for the Detection and Analysis of Historical Discourses","funder_award_id":"347707","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306750934.pdf","grobid_xml":"https://content.openalex.org/works/W4306750934.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1781770377","https://openalex.org/W1834987204","https://openalex.org/W1959000896","https://openalex.org/W1991418309","https://openalex.org/W2027731328","https://openalex.org/W2061873838","https://openalex.org/W2068074736","https://openalex.org/W2100743709","https://openalex.org/W2107275319","https://openalex.org/W2131462252","https://openalex.org/W2146502635","https://openalex.org/W2183087644","https://openalex.org/W2520348554","https://openalex.org/W2739996966","https://openalex.org/W2743021690","https://openalex.org/W2788125153","https://openalex.org/W2890634844","https://openalex.org/W2896214533","https://openalex.org/W2906963924","https://openalex.org/W2921113176","https://openalex.org/W2944514791","https://openalex.org/W2945136801","https://openalex.org/W2964054038","https://openalex.org/W2970449868","https://openalex.org/W2970574105","https://openalex.org/W3037422790","https://openalex.org/W3080802002","https://openalex.org/W3114079967","https://openalex.org/W3120771037","https://openalex.org/W3169488402","https://openalex.org/W3201691278","https://openalex.org/W4236362309","https://openalex.org/W6677656871","https://openalex.org/W6681654339"],"related_works":["https://openalex.org/W2379140333","https://openalex.org/W1592900392","https://openalex.org/W2163526212","https://openalex.org/W2036133907","https://openalex.org/W2394447189","https://openalex.org/W2539940072","https://openalex.org/W2092829304","https://openalex.org/W2538830880","https://openalex.org/W2366786074","https://openalex.org/W2364362706"],"abstract_inverted_index":{"Abstract":[0],"In":[1],"this":[2],"paper,":[3],"we":[4],"show":[5],"that":[6,66,97,119,160,180],"a":[7,55,107,135],"simple,":[8],"data":[9],"dependent":[10],"way":[11],"of":[12,26,39,47,57,102,113,138,158,191,195],"setting":[13],"the":[14,24,37,41,45,75,93,100,111,125,155,170,187,192,196,199],"initial":[15,42,94],"vector":[16,95],"can":[17,79,120,211],"be":[18,80,121,163,212],"used":[19],"to":[20,52,140,162,166,169,182],"substantially":[21],"speed":[22],"up":[23,139],"training":[25,136],"linear":[27],"one-versus-all":[28],"classifiers":[29],"in":[30,54,131,152,173,186,206],"extreme":[31],"multi-label":[32],"classification":[33,207],"(XMC).":[34],"We":[35,50,133],"discuss":[36],"problem":[38],"choosing":[40],"weights":[43],"from":[44,110,154,175],"perspective":[46],"three":[48],"goals.":[49],"want":[51],"start":[53],"region":[56],"weight":[58],"space":[59],"(a)":[60],"with":[61,147],"low":[62],"loss":[63],"value,":[64],"(b)":[65],"is":[67,89,201],"favourable":[68],"for":[69,106,124],"second-order":[70],"optimization,":[71],"and":[72,172],"(c)":[73],"where":[74],"conjugate-gradient":[76],"(CG)":[77],"calculations":[78],"performed":[81,164],"quickly.":[82],"For":[83],"margin":[84],"losses,":[85],"such":[86,96],"an":[87,176],"initialization":[88],"achieved":[90,202],"by":[91],"selecting":[92],"it":[98],"separates":[99],"mean":[101,112],"all":[103,114],"positive":[104],"(relevant":[105],"label)":[108],"instances":[109],"negatives":[115,185],"\u2013":[116],"two":[117],"quantities":[118],"calculated":[122],"quickly":[123],"highly":[126],"imbalanced":[127],"binary":[128],"problems":[129],"occurring":[130],"XMC.":[132],"demonstrate":[134],"speedup":[137,200],"$$5\\times$$":[141],"5":[142],"\u00d7":[143],"on":[144],"Amazon-670K":[145],"dataset":[146],"670,000":[148],"labels.":[149],"This":[150],"comes":[151],"part":[153,174],"reduced":[156],"number":[157],"iterations":[159],"need":[161],"due":[165],"starting":[167],"closer":[168],"solution,":[171],"implicit":[177],"negative-mining":[178],"effect":[179],"allows":[181],"ignore":[183],"easy":[184],"CG":[188],"step.":[189],"Because":[190],"convex":[193],"nature":[194],"optimization":[197],"problem,":[198],"without":[203],"any":[204],"degradation":[205],"accuracy.":[208],"The":[209],"implementation":[210],"found":[213],"at":[214],"https://github.com/xmc-aalto/dismecpp":[215],".":[216]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}