Dynamic Interpretability for Model Comparison via Decision Rules
This addresses the need for better model comparison tools in real-world applications like model selection and lifecycle management, though it is incremental as it builds on existing XAI methods.
The paper tackles the problem of explaining differences between multiple machine learning models, which is important for model selection and monitoring, by proposing DeltaXplainer, a model-agnostic method that generates rule-based explanations for binary classifiers, with experiments on synthetic and real-world datasets showing its effectiveness in various concept drift scenarios.
Explainable AI (XAI) methods have mostly been built to investigate and shed light on single machine learning models and are not designed to capture and explain differences between multiple models effectively. This paper addresses the challenge of understanding and explaining differences between machine learning models, which is crucial for model selection, monitoring and lifecycle management in real-world applications. We propose DeltaXplainer, a model-agnostic method for generating rule-based explanations describing the differences between two binary classifiers. To assess the effectiveness of DeltaXplainer, we conduct experiments on synthetic and real-world datasets, covering various model comparison scenarios involving different types of concept drift.