Causal Regularization Using Domain Priors

Neural networks leverage both causal and correlation-based relationships in data to learn models that optimize a given performance criterion, such as classification accuracy. This results in learned models that may not necessarily reflect the true causal relationships between input and output. When domain priors of causal relationships are available at the time of training, it is essential that a neural network model maintains these relationships as causal, even as it learns to optimize the performance criterion. We propose a causal regularization method that can incorporate such causal domain priors into the network and which supports both direct and total causal effects. We show that this approach can generalize to various kinds of specifications of causal priors, including monotonicity of causal effect of a given input feature or removing a certain influence for purposes of fairness. Our experiments on eleven benchmark datasets show the usefulness of this approach in regularizing a learned neural network model to maintain desired causal effects. On most datasets, domain-prior consistent models can be obtained without compromising on accuracy.