Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels

TL;DR

This paper introduces a unified gradient-based method for generating Local, Global, and Group-wise Counterfactual Explanations in AI, enhancing interpretability and trustworthiness across different explanation levels.

Contribution

It presents a novel integrated approach that combines instance grouping with counterfactual generation, improving efficiency and plausibility in explanations.

Findings

Effective balancing of validity, proximity, and plausibility in explanations

Unified method generates explanations at multiple levels simultaneously

Practical utility demonstrated through real-world use cases

Abstract

The growing complexity of AI systems has intensified the need for transparency through Explainable AI (XAI). Counterfactual explanations (CFs) offer actionable "what-if" scenarios on three levels: Local CFs providing instance-specific insights, Global CFs addressing broader trends, and Group-wise CFs (GWCFs) striking a balance and revealing patterns within cohesive groups. Despite the availability of methods for each granularity level, the field lacks a unified method that integrates these complementary approaches. We address this limitation by proposing a gradient-based optimization method for differentiable models that generates Local, Global, and Group-wise Counterfactual Explanations in a unified manner. We especially enhance GWCF generation by combining instance grouping and counterfactual generation into a single efficient process, replacing traditional two-step methods. Moreover, to ensure trustworthiness, we innovatively introduce the integration of plausibility criteria into the GWCF domain, making explanations both valid and realistic. Our results demonstrate the method's effectiveness in balancing validity, proximity, and plausibility while optimizing group granularity, with practical utility validated through practical use cases.