CoRTX: Contrastive Framework for Real-time Explanation

Understand

Recent advancements in explainable machine learning provide effective and faithful solutions for interpreting model behaviors.

• However, many explanation methods encounter efficiency issues, which largely limit their deployments in practical scenarios.
• Real-time explainer (RTX) frameworks have thus been proposed to accelerate the model explanation process by learning a one-feed-forward explainer.
• Existing RTX frameworks typically build the explainer under the supervised learning paradigm, which requires large amounts of explanation labels as the ground truth.