A Meta Learning Approach to Discerning Causal Graph Structure

Abstract

We explore the usage of meta-learning to derive the causal direction between variables by optimizing over a measure of distribution simplicity. We incorporate a stochastic graph representation which includes latent variables and allows for more generalizability and graph structure expression. Our model is able to learn causal direction indicators for complex graph structures despite effects of latent confounders. Further, we explore robustness of our method with respect to violations of our distributional assumptions and data scarcity. Our model is particularly robust to modest data scarcity, but is less robust to distributional changes. By interpreting the model predictions as stochastic events, we propose a simple ensemble method classifier to reduce the outcome variability as an average of biased events. This methodology demonstrates ability to infer the existence as well as the direction of a causal relationship between data distributions.

References in corpus (5)

• A Simple Framework for Contrastive Learning of Visual Representations
• Causal Effect Inference with Deep Latent-Variable Models
• A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
• Causal Generative Neural Networks
• Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data