Longitudinal Counterfactuals: Constraints and Opportunities
This work addresses the challenge of providing actionable recourse to data subjects in AI systems, though it is incremental by building on existing counterfactual explanation methods.
The paper tackles the problem of generating plausible counterfactual explanations for algorithmic recourse by proposing a method that uses longitudinal data to assess and improve plausibility, resulting in a metric and generation technique that compares counterfactual differences to prior observed changes.
Counterfactual explanations are a common approach to providing recourse to data subjects. However, current methodology can produce counterfactuals that cannot be achieved by the subject, making the use of counterfactuals for recourse difficult to justify in practice. Though there is agreement that plausibility is an important quality when using counterfactuals for algorithmic recourse, ground truth plausibility continues to be difficult to quantify. In this paper, we propose using longitudinal data to assess and improve plausibility in counterfactuals. In particular, we develop a metric that compares longitudinal differences to counterfactual differences, allowing us to evaluate how similar a counterfactual is to prior observed changes. Furthermore, we use this metric to generate plausible counterfactuals. Finally, we discuss some of the inherent difficulties of using counterfactuals for recourse.