Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 13 Feb 2025.
Builds on
27 of 44 references.
References · 27
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
- 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
- 2021Towards Causal Representation Learningcited by 209
- 2020Understanding the Failure Modes of Out-of-Distribution Generalizationcited by 146
- 2021On Calibration and Out-of-domain Generalizationcited by 134
- 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
15 more
- 2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
- 2024Robust agents learn causal world modelscited by 81
- 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
- 2022Agree to Disagree: Diversity through Disagreement for Better Transferabilitycited by 70
- 2023Prediction-Oriented Bayesian Active Learningcited by 62
- 2014Visual Causal Feature Learningcited by 59
- 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 42
- 2023A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methodscited by 32
- 2024Label-wise Aleatoric and Epistemic Uncertainty Quantificationcited by 22
- 2023Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Featurescited by 21
- 2024The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networkscited by 11
- 2022A Typology for Exploring the Mitigation of Shortcut Behaviorcited by 7
- 2022Monitoring Shortcut Learning using Mutual Informationcited by 6
- 2023Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensemblescited by 4
- 2024Mitigating Overconfidence in Out-of-Distribution Detection by Capturing Extreme Activationscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.