{"id":"https://openalex.org/W7162486132","doi":"https://doi.org/10.48550/arxiv.2605.26477","title":"Variational Inference for Evidential Deep Learning","display_name":"Variational Inference for Evidential Deep Learning","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162486132","doi":"https://doi.org/10.48550/arxiv.2605.26477"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26477","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":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.2605.26477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137147476","display_name":"Jiawei Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137090288","display_name":"Xinyan Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xinyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137146789","display_name":"Hui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137134128","display_name":"Junhui Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Junhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137092964","display_name":"Yuheng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Yuheng","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6546000242233276,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6546000242233276,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.14830000698566437,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.13099999725818634,"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/generalization","display_name":"Generalization","score":0.6761999726295471},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6642000079154968},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5927000045776367},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5027999877929688},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44929999113082886},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4115999937057495}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6761999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6717000007629395},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5613999962806702},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5027999877929688},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.37049999833106995},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3158999979496002},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26477","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26477","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":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":{"While":[0],"Deep":[1,15,94],"Neural":[2],"Networks":[3],"(DNNs)":[4],"achieve":[5],"remarkable":[6],"performance,":[7,165],"their":[8],"tendency":[9],"to":[10,30,68],"produce":[11],"overconfident":[12],"predictions.":[13],"Evidential":[14,93],"Learning":[16,95],"(EDL)":[17],"mitigates":[18],"this":[19,83,139],"by":[20],"formulating":[21],"predictions":[22],"as":[23],"a":[24,47,87,125],"Dirichlet":[25,79],"distribution":[26],"over":[27],"class":[28],"probabilities":[29],"explicitly":[31],"quantify":[32,69],"epistemic":[33],"uncertainty.":[34],"However,":[35],"we":[36,85,107,122],"found":[37],"that":[38,51,161],"the":[39,54,65,102,116,131],"conventional":[40],"EDL":[41],"suffers":[42],"from":[43,118],"two":[44],"fundamental":[45],"limitations:":[46],"Kullback-Leibler":[48],"(KL)":[49],"penalty":[50],"only":[52],"suppresses":[53],"evidence":[55,62,117],"of":[56,77,104],"negative":[57],"classes,":[58],"producing":[59],"excessively":[60],"high":[61],"therefore":[63],"decreasing":[64],"model's":[66],"ability":[67],"uncertainty,":[70,133],"and":[71,128,135,141,157,174],"an":[72,109],"absence":[73],"in":[74,169,182],"theoretical":[75],"guarantee":[76],"setting":[78,143],"parameter":[80],"$\u03b1=e+1$.":[81],"In":[82],"paper,":[84],"propose":[86],"mathematically":[88],"principled":[89],"framework,":[90],"Variational":[91],"Inference":[92],"(VI-EDL).":[96],"By":[97],"reformulating":[98],"evidential":[99],"learning":[100],"through":[101],"lens":[103],"variational":[105],"inference,":[106],"derive":[108],"Evidence":[110],"Lower":[111],"Bound":[112],"(ELBO),":[113],"which":[114],"prevents":[115],"growing":[119],"excessively.":[120],"Theoretically,":[121],"rigorously":[123],"establish":[124],"generalization":[126],"bound":[127],"reveal":[129],"how":[130],"predicted":[132],"feature":[134],"network":[136],"complexity":[137],"affect":[138],"bound,":[140],"why":[142],"$\\boldsymbol\u03b1":[144],"=":[145],"\\mathbf{e}":[146],"+":[147],"\\mathbf{1}$":[148],"can":[149],"minimize":[150],"it.":[151],"Extensive":[152],"experiments":[153],"on":[154],"standard":[155],"visual":[156],"medical":[158],"datasets":[159],"demonstrate":[160],"VI-EDL":[162],"achieves":[163],"state-of-the-art":[164],"showing":[166],"excellent":[167],"performance":[168],"out-of-distribution":[170],"detection,":[171],"noise":[172],"detection":[173],"autonomous":[175],"driving":[176],"scenario.":[177],"The":[178],"code":[179],"is":[180],"available":[181],"https://github.com/seutjw/VI-EDL.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}