6 papers
Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion
David Bechtoldt, Sidney Bender
Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no int…
Graph Diffusion Counterfactual Explanation
David Bechtoldt, Sidney Bender
Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certai…
Imbalanced Classification through the Lens of Spurious Correlations
Jakob Hackstein, Sidney Bender
Class imbalance poses a fundamental challenge in machine learning, frequently leading to unreliable classification performance. While prior methods focus on data- or loss-reweighti…
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
Sidney Bender, Ole Delzer, Jan Herrmann +3
Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-super…
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Sidney Bender, Jan Herrmann, Klaus-Robert Müller +1
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations…
Diffusion Counterfactuals for Image Regressors
Trung Duc Ha, Sidney Bender
Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, wh…