Causality Learning: A New Perspective for Interpretable Machine Learning

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.

8 Pages

References in corpus (12)

• Towards A Rigorous Science of Interpretable Machine Learning
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Actionable Recourse in Linear Classification
• Metrics for Explainable AI: Challenges and Prospects
• GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
• Explaining Classifiers with Causal Concept Effect (CaCE)
• CausalML: Python Package for Causal Machine Learning
• Causal Discovery Toolbox: Uncover causal relationships in Python
• Counterfactuals uncover the modular structure of deep generative models
• Explaining Deep Learning Models using Causal Inference
• Multi-Value Rule Sets
• Uplift Modeling with Multiple Treatments and General Response Types

Cited by in corpus (5)

• Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications
• REX: Causal discovery based on machine learning and explainability techniques
• Temporal Meta-path Guided Explainable Recommendation
• Causal Learning for Socially Responsible AI
• Stochastic Intervention for Causal Effect Estimation