Pyreal: A Framework for Interpretable ML Explanations
This addresses the problem of high development overhead for interpretable ML explanations for users in decision-making domains, though it appears incremental as it builds on existing explanation algorithms.
The authors tackled the challenge of generating comprehensible and useful explanations for machine learning predictions by developing Pyreal, a framework that converts data and explanations across different feature spaces, resulting in more useful explanations than existing systems while being easy-to-use and efficient.
Users in many domains use machine learning (ML) predictions to help them make decisions. Effective ML-based decision-making often requires explanations of ML models and their predictions. While there are many algorithms that explain models, generating explanations in a format that is comprehensible and useful to decision-makers is a nontrivial task that can require extensive development overhead. We developed Pyreal, a highly extensible system with a corresponding Python implementation for generating a variety of interpretable ML explanations. Pyreal converts data and explanations between the feature spaces expected by the model, relevant explanation algorithms, and human users, allowing users to generate interpretable explanations in a low-code manner. Our studies demonstrate that Pyreal generates more useful explanations than existing systems while remaining both easy-to-use and efficient.