On the Robustness of Global Feature Effect Explanations

2024-06-13

ECML/PKDD

AI Summary

This study addresses the robustness of global post-hoc interpretability methods—such as Partial Dependence Plots (PDP) and Accumulated Local Effects (ALE)—for black-box predictive models on tabular data under data and model perturbations. Motivated by reliability deficits arising from their fragility in model debugging and scientific discovery, we propose the first theoretical bounds quantifying explanation deviation under worst-case and best-case perturbations. Our approach integrates rigorous theoretical analysis with extensive empirical evaluation across multiple real-world and synthetic datasets, systematically assessing explanation sensitivity to controlled perturbations. Results demonstrate that even minor perturbations can substantially distort global feature effect estimates—up to complete reversal of effect direction in adversarial cases. This work establishes the first formal robustness framework for global interpretability, filling a critical gap in the theoretical foundations of trustworthy XAI. It provides the first quantifiable diagnostic benchmark for evaluating the stability and fidelity of global explanations.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.

Problem

• Study robustness of global post-hoc explanations for tabular data models
• Assess vulnerability of feature effects to data and model perturbations
• Quantify gap between best and worst-case interpretation scenarios

Innovation

• Theoretical bounds for robustness evaluation
• Analyzing partial dependence plots robustness
• Quantifying global prediction interpretation gaps