VI-EDL reformulates evidential deep learning via variational inference to derive an ELBO that limits excessive evidence and a generalization bound that justifies setting Dirichlet parameters to e+1.
unit-evidence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Variational Inference for Evidential Deep Learning
VI-EDL reformulates evidential deep learning via variational inference to derive an ELBO that limits excessive evidence and a generalization bound that justifies setting Dirichlet parameters to e+1.