Saved in:
Bibliographic Details
Main Authors: Gjølbye, Anders, Haufe, Stefan, Hansen, Lars Kai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.11210
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908610567602176
author Gjølbye, Anders
Haufe, Stefan
Hansen, Lars Kai
author_facet Gjølbye, Anders
Haufe, Stefan
Hansen, Lars Kai
contents 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 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. We further evaluate PatternLocal on an EEG motor imagery dataset, demonstrating physiologically plausible explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Minimizing False-Positive Attributions in Explanations of Non-Linear Models
Gjølbye, Anders
Haufe, Stefan
Hansen, Lars Kai
Machine Learning
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 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. We further evaluate PatternLocal on an EEG motor imagery dataset, demonstrating physiologically plausible explanations.
title Minimizing False-Positive Attributions in Explanations of Non-Linear Models
topic Machine Learning
url https://arxiv.org/abs/2505.11210