Causal Regularization

• Published in: arXiv.org 2017-02
• Main Authors: Mohammad Taha Bahadori, Chalupka, Krzysztof, Choi, Edward, Chen, Robert, Stewart, Walter F, Sun, Jimeng
• Format: Article
• Language: English
• Subjects: Algorithms; Causation; Domains; Electronic health records; Health care; Machine learning; Mathematical models; Multilayer perceptrons; Neural networks; Nonlinear analysis; Performance prediction; Regularization
• ISSN: 2331-8422

In application domains such as healthcare, we want accurate predictive models that are also causally interpretable. In pursuit of such models, we propose a causal regularizer to steer predictive models towards causally-interpretable solutions and theoretically study its properties. In a large-scale analysis of Electronic Health Records (EHR), our causally-regularized model outperforms its L1-regularized counterpart in causal accuracy and is competitive in predictive performance. We perform non-linear causality analysis by causally regularizing a special neural network architecture. We also show that the proposed causal regularizer can be used together with neural representation learning algorithms to yield up to 20% improvement over multilayer perceptron in detecting multivariate causation, a situation common in healthcare, where many causal factors should occur simultaneously to have an effect on the target variable.