Masked Gradient-Based Causal Structure Learning
This addresses the problem of efficient causal discovery for researchers and practitioners, but it is incremental as it builds on existing gradient-based and approximation techniques.
The paper tackles learning causal structures from observational data by reformulating the Structural Equation Model with additive noises and developing a gradient-based optimization method using smooth acyclicity and Gumbel-Softmax approximations, achieving much improved performance on most datasets.
This paper studies the problem of learning causal structures from observational data. We reformulate the Structural Equation Model (SEM) with additive noises in a form parameterized by binary graph adjacency matrix and show that, if the original SEM is identifiable, then the binary adjacency matrix can be identified up to super-graphs of the true causal graph under mild conditions. We then utilize the reformulated SEM to develop a causal structure learning method that can be efficiently trained using gradient-based optimization, by leveraging a smooth characterization on acyclicity and the Gumbel-Softmax approach to approximate the binary adjacency matrix. It is found that the obtained entries are typically near zero or one and can be easily thresholded to identify the edges. We conduct experiments on synthetic and real datasets to validate the effectiveness of the proposed method, and show that it readily includes different smooth model functions and achieves a much improved performance on most datasets considered.