PWSHAP: A Path-Wise Explanation Model for Targeted Variables
This addresses the need for tailored explanation methods in safety-critical domains, such as clinical or policy models, but is incremental as it builds on existing Shapley value techniques.
The authors tackled the problem of explaining black-box models in sensitive domains where a specific predictor, like a treatment effect, is of interest, by introducing PWSHAP, a framework that uses a user-defined DAG and on-manifold Shapley values to assess targeted effects, establishing error bounds and demonstrating its capabilities in local bias and mediation analyses.
Predictive black-box models can exhibit high accuracy but their opaque nature hinders their uptake in safety-critical deployment environments. Explanation methods (XAI) can provide confidence for decision-making through increased transparency. However, existing XAI methods are not tailored towards models in sensitive domains where one predictor is of special interest, such as a treatment effect in a clinical model, or ethnicity in policy models. We introduce Path-Wise Shapley effects (PWSHAP), a framework for assessing the targeted effect of a binary (e.g.~treatment) variable from a complex outcome model. Our approach augments the predictive model with a user-defined directed acyclic graph (DAG). The method then uses the graph alongside on-manifold Shapley values to identify effects along causal pathways whilst maintaining robustness to adversarial attacks. We establish error bounds for the identified path-wise Shapley effects and for Shapley values. We show PWSHAP can perform local bias and mediation analyses with faithfulness to the model. Further, if the targeted variable is randomised we can quantify local effect modification. We demonstrate the resolution, interpretability, and true locality of our approach on examples and a real-world experiment.