Generating Counterfactual and Contrastive Explanations using SHAP
This addresses the need for interpretable AI in compliance with regulations, but it appears incremental as it builds on existing SHAP methods for explanation generation.
The paper tackles the problem of generating contrastive and counterfactual explanations for AI models to meet legal requirements like GDPR, proposing a model-agnostic method using SHAP and testing it on datasets such as IRIS, Wine Quality, and Mobile Features.
With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.