Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels
For XAI practitioners, it provides a single method to generate counterfactuals across all granularity levels, addressing the lack of unification, though the approach is incremental.
The paper proposes a unified gradient-based method to generate counterfactual explanations at local, global, and group-wise levels for differentiable models, integrating plausibility into group-wise explanations. Results show effectiveness in balancing validity, proximity, and plausibility, validated through use cases.
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.