Causality Learning: A New Perspective for Interpretable Machine Learning

TL;DR

This paper explores how causal analysis can enhance interpretability in machine learning, addressing the limitations of traditional association-based methods and discussing recent advances, evaluation techniques, and open challenges.

Contribution

It provides a comprehensive overview of causal approaches in interpretable machine learning, highlighting recent methods and discussing evaluation and open problems.

Findings

Causal analysis offers a promising direction for interpretability.

Recent causal methods improve understanding of ML models.

Open problems remain in causal interpretability evaluation.

Abstract

Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in different sectors, researchers still concern about the mechanism under any machine learning (ML) techniques that are inherently black-box and becoming more complex to achieve higher accuracy. Therefore, interpreting machine learning model is currently a mainstream topic in the research community. However, the traditional interpretable machine learning focuses on the association instead of the causality. This paper provides an overview of causal analysis with the fundamental background and key concepts, and then summarizes most recent causal approaches for interpretable machine learning. The evaluation techniques for assessing method quality, and open problems in causal interpretability are also discussed in this paper.