Causality-based Feature Selection: Methods and Evaluations
arXiv:1911.07147
Abstract
Feature selection is a crucial preprocessing step in data analytics and machine learning. Classical feature selection algorithms select features based on the correlations between predictive features and the class variable and do not attempt to capture causal relationships between them. It has been shown that the knowledge about the causal relationships between features and the class variable has potential benefits for building interpretable and robust prediction models, since causal relationships imply the underlying mechanism of a system. Consequently, causality-based feature selection has gradually attracted greater attentions and many algorithms have been proposed. In this paper, we present a comprehensive review of recent advances in causality-based feature selection. To facilitate the development of new algorithms in the research area and make it easy for the comparisons between new methods and existing ones, we develop the first open-source package, called CausalFS, which consists of most of the representative causality-based feature selection algorithms (available at https://github.com/kuiy/CausalFS). Using CausalFS, we conduct extensive experiments to compare the representative algorithms with both synthetic and real-world data sets. Finally, we discuss some challenging problems to be tackled in future causality-based feature selection research.
References in corpus (9)
- Kernel-based Conditional Independence Test and Application in Causal Discovery
- A Survey of Learning Causality with Data: Problems and Methods
- Invariant Models for Causal Transfer Learning
- Learning Bayesian Networks with the bnlearn R Package
- Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions
- Local Structure Discovery in Bayesian Networks
- Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
- Bayesian Structure Learning by Recursive Bootstrap
- Discovering Markov Blanket from Multiple interventional Datasets