The Definitions of Interpretability and Learning of Interpretable Models

2021/05/29 by Pan, Weishen, Zhang, Changshui
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2105.14171

Abstract

As machine learning algorithms getting adopted in an ever-increasing number of applications, interpretation has emerged as a crucial desideratum. In this paper, we propose a mathematical definition for the human-interpretable model. In particular, we define interpretability between two information process systems. If a prediction model is interpretable by a human recognition system based on the above interpretability definition, the prediction model is defined as a completely human-interpretable model. We further design a practical framework to train a completely human-interpretable model by user interactions. Experiments on image datasets show the advantages of our proposed model in two aspects: 1) The completely human-interpretable model can provide an entire decision-making process that is human-understandable; 2) The completely human-interpretable model is more robust against adversarial attacks.

Related

• Techniques for Interpretable Machine Learning
• Towards A Rigorous Science of Interpretable Machine Learning
• A Bayesian Account of Measures of Interpretability in Human-AI Interaction
• Foundations of Interpretable Models
• Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond