Suppressor variables can influence model predictions without being dependent on the target outcome and they pose a significant challenge for Explainable AI (XAI) methods. These variables may cause false-positive feature attributions, undermining the utility of explanations. Although effective remedies exist for linear models, their extension to non-linear models and to instance-based explanations has remained limited. We introduce PatternLocal, a novel XAI technique that addresses this gap. PatternLocal begins with a locally linear surrogate, e.g. LIME, KernelSHAP, or gradient-based methods, and transforms the resulting discriminative model weights into a generative representation, thereby suppressing the influence of suppressor variables while preserving local fidelity. In extensive hyperparameter optimization on the XAI-TRIS benchmark, PatternLocal consistently outperformed other XAI methods and reduced false-positive attributions when explaining non-linear tasks, thereby enabling more reliable and actionable insights.
View on arXiv@article{gjølbye2025_2505.11210,
title={ Minimizing False-Positive Attributions in Explanations of Non-Linear Models },
author={ Anders Gjølbye and Stefan Haufe and Lars Kai Hansen },
journal={arXiv preprint arXiv:2505.11210},
year={ 2025 }
}