Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
This addresses the inefficiency of retraining models for each new causal graph in time-series analysis, offering a more scalable approach for researchers and practitioners in fields like healthcare or economics.
The paper tackles the problem of causal discovery from time-series data by proposing Amortized Causal Discovery, a framework that trains a single model to infer causal relations across samples with different underlying graphs, leveraging shared dynamics. The result is significant improvements in performance, with extensions showing robustness to noise and hidden confounding.
On time-series data, most causal discovery methods fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information which is lost when following this approach. Specifically, different samples may share the dynamics which describe the effects of their causal relations. We propose Amortized Causal Discovery, a novel framework that leverages such shared dynamics to learn to infer causal relations from time-series data. This enables us to train a single, amortized model that infers causal relations across samples with different underlying causal graphs, and thus leverages the shared dynamics information. We demonstrate experimentally that this approach, implemented as a variational model, leads to significant improvements in causal discovery performance, and show how it can be extended to perform well under added noise and hidden confounding.