DeepAI AI Chat
Log In Sign Up

Causal Regularization

by   Mohammad Taha Bahadori, et al.

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 multivariate causation, a situation common in healthcare, where many causal factors should occur simultaneously to have an effect on the target variable.


page 1

page 2

page 3

page 4


Causal Inference via Nonlinear Variable Decorrelation for Healthcare Applications

Causal inference and model interpretability research are gaining increas...

Unifying Heterogenous Electronic Health Records Systems via Text-Based Code Embedding

Substantial increase in the use of Electronic Health Records (EHRs) has ...

Neural Network Attributions: A Causal Perspective

We propose a new attribution method for neural networks developed using ...

Causality Inspired Representation Learning for Domain Generalization

Domain generalization (DG) is essentially an out-of-distribution problem...

Trading-Off Cost of Deployment Versus Accuracy in Learning Predictive Models

Predictive models are finding an increasing number of applications in ma...

The Causal Loss: Driving Correlation to Imply Causation

Most algorithms in classical and contemporary machine learning focus on ...