Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
Abstract
The correct way to quantify predictive uncertainty in neural networks remains a topic of active discussion. In particular, it is unclear whether the state-of-the art entropy decomposition leads to a meaningful representation of model, or *epistemic*, uncertainty (EU) in the light of a debate that pits *ignorance* against *disagreement* perspectives. We aim to reconcile the conflicting viewpoints by arguing that both are valid but arise from different learning situations. Notably, we show that the presence of *shortcuts* is decisive for EU manifesting as disagreement.
Cite
Text
Wimmer et al. "Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning." ICLR 2025 Workshops: SCSL, 2025.Markdown
[Wimmer et al. "Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning." ICLR 2025 Workshops: SCSL, 2025.](https://mlanthology.org/iclrw/2025/wimmer2025iclrw-trust/)BibTeX
@inproceedings{wimmer2025iclrw-trust,
title = {{Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning}},
author = {Wimmer, Lisa and Bischl, Bernd and Bothmann, Ludwig},
booktitle = {ICLR 2025 Workshops: SCSL},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/wimmer2025iclrw-trust/}
}