{"id":"https://openalex.org/W7140077565","doi":"https://doi.org/10.48550/arxiv.2603.19653","title":"Ensembles-based Feature Guided Analysis","display_name":"Ensembles-based Feature Guided Analysis","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140077565","doi":"https://doi.org/10.48550/arxiv.2603.19653"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19653","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.19653","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069902157","display_name":"Federico Formica","orcid":"https://orcid.org/0000-0002-3033-7371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Formica, Federico","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130326402","display_name":"Stefano Gregis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregis, Stefano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120270567","display_name":"Andrea Rota","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rota, Andrea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119327509","display_name":"Aurora Francesca Zanenga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zanenga, Aurora Francesca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087660741","display_name":"Mark Lawford","orcid":"https://orcid.org/0000-0003-3161-2176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawford, Mark","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018466538","display_name":"Claudio Menghi","orcid":"https://orcid.org/0000-0001-5303-8481"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Menghi, Claudio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.974399983882904,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.974399983882904,"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":0.0024999999441206455,"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/T14347","display_name":"Big Data and Digital Economy","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/feature","display_name":"Feature (linguistics)","score":0.690500020980835},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.6643000245094299},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.6290000081062317},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5544000267982483},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5378000140190125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4223000109195709},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.38940000534057617}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700999736785889},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.633400022983551},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.6290000081062317},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47699999809265137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C32172795","wikidata":"https://www.wikidata.org/wiki/Q4692266","display_name":"Aggregation problem","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19653","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.19653","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19653","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"Deep":[1],"Neural":[2],"Networks":[3],"(DNN)":[4],"applications":[5],"ask":[6],"for":[7],"techniques":[8],"that":[9,41,104,159,184,196],"can":[10,121],"explain":[11],"their":[12,25,95],"behavior.":[13],"Existing":[14],"solutions,":[15],"such":[16],"as":[17],"Feature":[18,77],"Guided":[19,78],"Analysis":[20,79],"(FGA),":[21],"extract":[22],"rules":[23,43,83,92,109],"on":[24,98,148,203,206,212,215,223,228,231],"internal":[26],"behaviors,":[27],"e.g.,":[28],"by":[29,85,124],"providing":[30],"explanations":[31],"related":[32],"to":[33,93,107],"neurons":[34],"activation.":[35],"Results":[36],"from":[37],"the":[38,56,59,138,141,144,152,224],"literature":[39],"show":[40,195],"these":[42,63],"have":[44],"considerable":[45],"precision":[46,167,190,226],"(i.e.,":[47,58,151],"they":[48],"correctly":[49],"predict":[50],"certain":[51],"classes":[52],"of":[53,61,140,146],"features),":[54],"but":[55],"recall":[57,201,210],"number":[60],"situations":[62],"rule":[64],"apply)":[65],"is":[66,115],"more":[67],"limited.":[68],"To":[69],"mitigate":[70],"this":[71,73,127,177],"problem,":[72],"paper":[74],"presents":[75],"Ensembles-based":[76],"(EFGA).":[80],"EFGA":[81,147,173,197],"combines":[82],"extracted":[84],"FGA":[86],"into":[87,110],"ensembles.":[88,111],"Ensembles":[89],"aggregate":[90],"different":[91,118,132,160],"increase":[94],"applicability":[96],"depending":[97],"an":[99,181],"aggregation":[100,119,133,161,182],"criterion,":[101],"a":[102,186,220],"policy":[103],"dictates":[105],"how":[106,137],"combine":[108],"Although":[112],"our":[113],"solution":[114],"extensible,":[116],"and":[117,154,157,168,191,208],"criteria":[120,162],"be":[122],"developed":[123],"users,":[125],"in":[126],"work,":[128],"we":[129,179],"considered":[130],"three":[131],"criteria.":[134],"We":[135,170],"evaluated":[136],"choice":[139],"criterion":[142,183],"influences":[143],"effectiveness":[145],"two":[149],"benchmarks":[150],"MNIST":[153],"LSC":[155],"datasets),":[156],"found":[158],"offer":[163],"alternative":[164],"trade-offs":[165],"between":[166,189],"recall.":[169,192],"then":[171],"compare":[172],"with":[174,219],"FGA.":[175],"For":[176],"experiment,":[178],"selected":[180],"provides":[185],"reasonable":[187],"trade-off":[188],"Our":[193],"results":[194],"has":[198],"higher":[199],"train":[200],"(+28.51%":[202],"MNIST,":[204,213,229],"+33.15%":[205],"LSC),":[207],"test":[209,225],"(+25.76%":[211],"+30.81%":[214],"LSC)":[216],"than":[217],"FGA,":[218],"negligible":[221],"reduction":[222],"(-0.89%":[227],"-0.69%":[230],"LSC).":[232]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-24T00:00:00"}