Discovering Invariant and Changing Mechanisms from Data

Summary

While invariance of causal mechanisms has inspired recent work in both robust machine learning and causal inference, causal mech- anisms often vary over domains due to, for example, population- specific differences, the context of data collection, or intervention. To discover invariant and changing mechanisms from data, we pro- pose extending the algorithmic model for causation to mechanism changes and instantiating it via Minimum Description Length. In essence, for a continuous variable ???? in multiple contexts C, we identify variables ???? as causal if the regression functions ???? : ???? → ???? have succinct descriptions in all contexts. In empirical evaluations we show that our method, Vario, reveals mechanism changes, dis- covers causal variables by invariance, and finds causal networks, such as on real-world data that gives insight into the signaling pathways in human immune cells.