Disentangle aleatoric and epistemic uncertainty in F-EDL

Develop a methodology within flexible evidential deep learning (F-EDL) to achieve full disentanglement of aleatoric uncertainty and epistemic uncertainty, surpassing the current variance-based decomposition and yielding structurally separated, interpretable components.

Background

F-EDL introduces label-wise variance-based uncertainty measures and a decomposition into aleatoric and epistemic components. However, the authors note that this decomposition does not fully disentangle the two sources of uncertainty, which is a longstanding challenge in UQ.

A complete disentanglement would enhance interpretability and reliability, especially in complex or noisy scenarios, and could improve downstream tasks such as misclassification and distribution shift detection.

References

Despite its improved flexibility, $\mathcal{F}$-EDL faces several open challenges. Second, although $\mathcal{F}$-EDL provides a variance-based decomposition of uncertainty, it does not fully disentangle aleatoric and epistemic components---highlighting the need for further work on structured disentanglement, a longstanding challenge in UQ .

— Uncertainty Estimation by Flexible Evidential Deep Learning  (2510.18322 - Yoon et al., 21 Oct 2025) in Conclusion, Limitations and Future Directions

A systematic validation, via a reparameterized sampler or an ensemble of independently seeded MAP fits, is a natural extension we leave to future work.

— Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment  (2609.21992 - Skorski, 18 Sep 2026) in Limitations, paragraph “Aleatoric/epistemic decomposition”