Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherence

TL;DR

This paper introduces CoDiCE, a novel method for generating counterfactual explanations that incorporates diffusion distance and directional coherence biases, improving human-centric explanation quality in AI models.

Contribution

The paper proposes two new biases, diffusion distance and directional coherence, to enhance counterfactual explanation search, inspired by human cognition insights.

Findings

CoDiCE outperforms existing methods like DiCE and FACE in experiments.

The approach improves the feasibility and interpretability of counterfactual explanations.

Ablation studies confirm the effectiveness of the proposed biases.

Abstract

A pressing issue in the adoption of AI models is the increasing demand for more human-centric explanations of their predictions. To advance towards more human-centric explanations, understanding how humans produce and select explanations has been beneficial. In this work, inspired by insights of human cognition we propose and test the incorporation of two novel biases to enhance the search for effective counterfactual explanations. Central to our methodology is the application of diffusion distance, which emphasizes data connectivity and actionability in the search for feasible counterfactual explanations. In particular, diffusion distance effectively weights more those points that are more interconnected by numerous short-length paths. This approach brings closely connected points nearer to each other, identifying a feasible path between them. We also introduce a directional coherence term that allows the expression of a preference for the alignment between the joint and marginal directional changes in feature space to reach a counterfactual. This term enables the generation of counterfactual explanations that align with a set of marginal predictions based on expectations of how the outcome of the model varies by changing one feature at a time. We evaluate our method, named Coherent Directional Counterfactual Explainer (CoDiCE), and the impact of the two novel biases against existing methods such as DiCE, FACE, Prototypes, and Growing Spheres. Through a series of ablation experiments on both synthetic and real datasets with continuous and mixed-type features, we demonstrate the effectiveness of our method.