paper-with-me

홈 › Papers

Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables

2023-06-02 · Rick Wilming, Leo Kieslich, Benedict Clark, Stefan Haufe

In recent years, the community of 'explainable artificial intelligence' (XAI) has created a vast body of methods to bridge a perceived gap between model 'complexity' and 'interpretability'. However, a concrete problem to be solved by XAI methods has not yet been formally stated. As a result, XAI methods are lacking theoretical and empirical evidence for the 'correctness' of their explanations, limiting their potential use for quality-control and transparency purposes. At the same time, Haufe et al. (2014) showed, using simple toy examples, that even standard interpretations of linear models can be highly misleading. Specifically, high importance may be attributed to so-called suppressor variables lacking any statistical relation to the prediction target. This behavior has been confirmed empirically for a large array of XAI methods in Wilming et al. (2022). Here, we go one step further by deriving analytical expressions for the behavior of a variety of popular XAI methods on a simple two-dimensional binary classification problem involving Gaussian class-conditional distributions. We show that the majority of the studied approaches will attribute non-zero importance to a non-class-related suppressor feature in the presence of correlated noise. This poses important limitations on the interpretations and conclusions that the outputs of these XAI methods can afford.

📄 PDF Abstract BibTeX arXiv:2306.01464

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeBinary ClassificationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Similar Papers 제목 키워드 기반

Scrutinizing XAI using linear ground-truth data with suppressor variables

2021-11-14 · Rick Wilming, Céline Budding, Klaus-Robert Müller, Stefan Haufe

Machine learning (ML) is increasingly often used to inform high-stakes decisions. As complex ML models (e.g., deep neural networks) are often considered black boxes, a wealth of procedures has been developed to shed ligh…

Explainable Artificial Intelligence (XAI)Feature Importance

Minimizing False-Positive Attributions in Explanations of Non-Linear Models

2025-05-16 · Anders Gjølbye, Stefan Haufe, Lars Kai Hansen

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 …

Hyperparameter Optimization

The effect of whitening on explanation performance

2026-02-09 · Benedict Clark, Stoyan Karastoyanov, Rick Wilming, Stefan Haufe arxiv

Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et …

Discovery of Causal Additive Models in the Presence of Unobserved Variables

2021-06-04 · Takashi Nicholas Maeda, Shohei Shimizu

Causal discovery from data affected by unobserved variables is an important but difficult problem to solve. The effects that unobserved variables have on the relationships between observed variables are more complex in n…

Additive modelsCausal Discovery

Weak Instrumental Variables: Limitations of Traditional 2SLS and Exploring Alternative Instrumental Variable Estimators

2021-04-26 · Aiwei Huang, Madhurima Chandra, Laura Malkhasyan

Instrumental variables estimation has gained considerable traction in recent decades as a tool for causal inference, particularly amongst empirical researchers. This paper makes three contributions. First, we provide a d…

Causal Inference