Invariant Structure Learning for Better Generalization and Causal Explainability
Abstract
Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Learning (ISL), that is designed to improve causal structure discovery by utilizing generalization as an indication. ISL splits the data into different environments, and learns a structure that is invariant to the target across different environments by imposing a consistency constraint. An aggregation mechanism then selects the optimal classifier based on a graph structure that reflects the causal mechanisms in the data more accurately compared to the structures learnt from individual environments. Furthermore, we extend ISL to a self-supervised learning setting where accurate causal structure discovery does not rely on any labels. This self-supervised ISL utilizes invariant causality proposals by iteratively setting different nodes as targets. On synthetic and real-world datasets, we demonstrate that ISL accurately discovers the causal structure, outperforms alternative methods, and yields superior generalization for datasets with significant distribution shifts.
Cite
@article{arxiv.2206.06469,
title = {Invariant Structure Learning for Better Generalization and Causal Explainability},
author = {Yunhao Ge and Sercan Ö. Arik and Jinsung Yoon and Ao Xu and Laurent Itti and Tomas Pfister},
journal= {arXiv preprint arXiv:2206.06469},
year = {2022}
}
Comments
16 pages (including Appendix), 4 figures