DeepAI AI Chat
Log In Sign Up

Scrutinizing XAI using linear ground-truth data with suppressor variables

by   Rick Wilming, et al.

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 light on their inner workings and the ways in which their predictions come about, defining the field of 'explainable AI' (XAI). Saliency methods rank input features according to some measure of 'importance'. Such methods are difficult to validate since a formal definition of feature importance is, thus far, lacking. It has been demonstrated that some saliency methods can highlight features that have no statistical association with the prediction target (suppressor variables). To avoid misinterpretations due to such behavior, we propose the actual presence of such an association as a necessary condition and objective preliminary definition for feature importance. We carefully crafted a ground-truth dataset in which all statistical dependencies are well-defined and linear, serving as a benchmark to study the problem of suppressor variables. We evaluate common explanation methods including LRP, DTD, PatternNet, PatternAttribution, LIME, Anchors, SHAP, and permutation-based methods with respect to our objective definition. We show that most of these methods are unable to distinguish important features from suppressors in this setting.


page 9

page 17

page 18

page 19


Evaluating Adversarial Robustness for Deep Neural Network Interpretability using fMRI Decoding

While deep neural networks (DNNs) are being increasingly used to make pr...

ECG Feature Importance Rankings: Cardiologists vs. Algorithms

Feature importance methods promise to provide a ranking of features acco...

Evaluating the Correctness of Explainable AI Algorithms for Classification

Explainable AI has attracted much research attention in recent years wit...

Feature Importance Measure for Non-linear Learning Algorithms

Complex problems may require sophisticated, non-linear learning methods ...

Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process

Scientists and practitioners increasingly rely on machine learning to mo...

The Berkelmans-Pries Feature Importance Method: A Generic Measure of Informativeness of Features

Over the past few years, the use of machine learning models has emerged ...

Shared Interest: Large-Scale Visual Analysis of Model Behavior by Measuring Human-AI Alignment

Saliency methods – techniques to identify the importance of input featur...