Bayesian Hierarchical Models for Counterfactual Estimation
This addresses the need for actionable and fair recourse in AI systems, offering an incremental improvement over single-point solutions.
The paper tackled the problem of generating multiple diverse counterfactual explanations for decisions by proposing a probabilistic paradigm that treats perturbations as random variables, resulting in valid, sparse, diverse, and feasible counterfactuals across several datasets.
Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse. We argue that it is beneficial to provide several alternative explanations rather than a single point solution and propose a probabilistic paradigm to estimate a diverse set of counterfactuals. Specifically, we treat the perturbations as random variables endowed with prior distribution functions. This allows sampling multiple counterfactuals from the posterior density, with the added benefit of incorporating inductive biases, preserving domain specific constraints and quantifying uncertainty in estimates. More importantly, we leverage Bayesian hierarchical modeling to share information across different subgroups of a population, which can both improve robustness and measure fairness. A gradient based sampler with superior convergence characteristics efficiently computes the posterior samples. Experiments across several datasets demonstrate that the counterfactuals estimated using our approach are valid, sparse, diverse and feasible.