Gradient-based Counterfactual Explanations using Tractable Probabilistic Models
This work addresses the need for efficient and realistic post-hoc explanations in machine learning, particularly for interpretability, but it is incremental as it builds on existing counterfactual methods with a novel optimization technique.
The paper tackles the problem of generating counterfactual explanations for machine learning models, which are slow and unrealistic with current methods, by proposing a gradient-based approach using tractable probabilistic models that requires only two gradient computations, resulting in faster and more realistic examples as demonstrated empirically.
Counterfactual examples are an appealing class of post-hoc explanations for machine learning models. Given input $x$ of class $y_1$, its counterfactual is a contrastive example $x^\prime$ of another class $y_0$. Current approaches primarily solve this task by a complex optimization: define an objective function based on the loss of the counterfactual outcome $y_0$ with hard or soft constraints, then optimize this function as a black-box. This "deep learning" approach, however, is rather slow, sometimes tricky, and may result in unrealistic counterfactual examples. In this work, we propose a novel approach to deal with these problems using only two gradient computations based on tractable probabilistic models. First, we compute an unconstrained counterfactual $u$ of $x$ to induce the counterfactual outcome $y_0$. Then, we adapt $u$ to higher density regions, resulting in $x^{\prime}$. Empirical evidence demonstrates the dominant advantages of our approach.