DICF: Domain-Invariant Counterfactual Explanations

Overview & Synopsis

One desired property of counterfactual explanations is plausibility, that is, a resemblance to real-world data. This property can be achieved by constraining counterfactuals lying in the data manifold. Unfortunately, the data often comes from multiple distinct environments (or domains) or changes under distribution shifts. This may alter the counterfactual validity and plausibility. To address this issue, we propose Domain-Invariant Counterfactual Explanations (DICF), a novel self-explaining framework rooted in invariant representation learning. By explicitly disentangling the latent representation into an invariant class space and a domain space, DICF enables counterfactual search within a predictive space, while preserving the domain specificities. We also introduce a dedicated mechanism to learn the distribution of unseen domains. Empirical evaluations on several datasets demonstrate that when the underlying assumption of class and domain independence holds, such as in image data, DICF finds a trade-off between minimizing feature perturbations and maximizing domain preservation. Furthermore, in mixed-type tabular environments, where domain and predictive features are inherently entangled, the framework remains competitive against state-of-theart baselines.