{"id":"https://openalex.org/W7224877446","doi":"https://doi.org/10.48550/arxiv.2610.39466","title":"CBE: A Complexity-adaptive Boundary-aware Ensemble Method for Imbalanced Data","display_name":"CBE: A Complexity-adaptive Boundary-aware Ensemble Method for Imbalanced Data","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224877446","doi":"https://doi.org/10.48550/arxiv.2610.39466"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39466","pdf_url":"https://arxiv.org/pdf/2610.39466","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39466","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102934921","display_name":"Xun Wei","orcid":"https://orcid.org/0000-0001-9828-6796","observed_orcids":["https://orcid.org/0000-0001-9828-6796"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei, Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5102934921"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994999766349792,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0003000000142492354,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.0,"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/class-imbalance","display_name":"class imbalance","score":0.7549999952316284},{"id":"https://openalex.org/keywords/undersampling","display_name":"undersampling","score":0.7799999713897705},{"id":"https://openalex.org/keywords/data-complexity","display_name":"data complexity","score":0.6430000066757202},{"id":"https://openalex.org/keywords/decision-boundaries","display_name":"decision boundaries","score":0.7689999938011169},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.8450000286102295},{"id":"https://openalex.org/keywords/complexity-measures","display_name":"complexity measures","score":0.7799999713897705},{"id":"https://openalex.org/keywords/class-overlap","display_name":"class overlap","score":0.4399999976158142}],"concepts":[{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.7089999914169312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6416000127792358},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.618399977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6082000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45210000872612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C40651066","wikidata":"https://www.wikidata.org/wiki/Q5048220","display_name":"Cascading classifiers","level":4,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39466","pdf_url":"https://arxiv.org/pdf/2610.39466","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.2610.39466","doi":"https://doi.org/10.48550/arxiv.2610.39466","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39466","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39466","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39466","pdf_url":"https://arxiv.org/pdf/2610.39466","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/W7224877446.pdf","grobid_xml":"https://content.openalex.org/works/W7224877446.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7170604603","https://openalex.org/W1527836356","https://openalex.org/W4411924658","https://openalex.org/W2081697244","https://openalex.org/W7098461590","https://openalex.org/W4404688916","https://openalex.org/W7004827690","https://openalex.org/W7168285197","https://openalex.org/W3000324184","https://openalex.org/W4399970693"],"abstract_inverted_index":{"In":[0],"many":[1,66,163],"real-world":[2],"classification":[3],"tasks,":[4],"datasets":[5,90,143,152],"exhibit":[6],"class":[7,39],"imbalance,":[8],"which":[9,63],"can":[10],"degrade":[11],"the":[12,34,55,108,118,159],"generalization":[13],"performance":[14,179],"of":[15,30,86,91,121,168],"conventional":[16],"learning":[17,31],"algorithms.":[18],"Data":[19],"complexity":[20,114,129],"has":[21,64],"recently":[22],"been":[23],"recognized":[24],"as":[25],"a":[26,100],"more":[27,48],"objective":[28],"indicator":[29],"difficulty":[32],"than":[33,50],"imbalance":[35,51],"ratio":[36],"alone,":[37],"because":[38],"overlap":[40],"and":[41,115,137,155,170,174],"complex":[42],"decision":[43,56],"boundaries":[44],"often":[45],"impair":[46],"classifiers":[47],"severely":[49],"itself.":[52],"Samples":[53],"near":[54],"boundary":[57,87,119],"are":[58],"inherently":[59],"difficult":[60],"to":[61,68,73,82,112,140],"classify,":[62],"motivated":[65],"researchers":[67],"focus":[69],"on":[70,149,172,180],"such":[71],"instances":[72],"improve":[74],"classifier":[75],"performance.":[76],"However,":[77],"most":[78],"under-sampling":[79,122],"approaches":[80],"fail":[81],"differentiate":[83],"their":[84],"sampling":[85,109],"samples":[88],"across":[89],"varying":[92],"complexity.":[93],"To":[94],"overcome":[95],"this":[96],"limitation,":[97],"we":[98],"propose":[99],"complexity-adaptive":[101],"boundary-aware":[102],"ensemble":[103],"(CBE)":[104],"framework":[105],"that":[106,131,158],"links":[107],"weight":[110],"distribution":[111],"data":[113],"dynamically":[116],"adjusts":[117],"preference":[120],"accordingly.":[123],"We":[124],"also":[125],"introduce":[126],"an":[127],"overall":[128],"measure":[130],"combines":[132],"metrics":[133],"at":[134],"multiple":[135],"levels":[136],"use":[138],"it":[139],"divide":[141],"imbalanced":[142],"into":[144],"three":[145],"categories.":[146],"Extensive":[147],"experiments":[148],"24":[150],"benchmark":[151],"from":[153],"UCI":[154],"KEEL":[156],"show":[157],"proposed":[160],"method":[161],"outperforms":[162],"existing":[164],"methods":[165],"in":[166],"terms":[167],"F-measure":[169],"G-mean":[171],"Easy":[173],"Median":[175],"datasets,":[176],"without":[177],"degrading":[178],"hard":[181],"cases.":[182]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}