DeepAI AI Chat
Log In Sign Up

Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data

by   Sindy Löwe, et al.

Standard causal discovery methods must fit a new model whenever they encounter samples from a new underlying causal graph. However, these samples often share relevant information - for instance, the dynamics describing the effects of causal relations - which is lost when following this approach. 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 makes use of the information that is shared. 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 hidden confounding.


page 1

page 2

page 3

page 4


Neural Additive Vector Autoregression Models for Causal Discovery in Time Series Data

Causal structure discovery in complex dynamical systems is an important ...

Learning LiNGAM based on data with more variables than observations

A very important topic in systems biology is developing statistical meth...

Causal Discovery from Subsampled Time Series Data by Constraint Optimization

This paper focuses on causal structure estimation from time series data ...

Inferring extended summary causal graphs from observational time series

This study addresses the problem of learning an extended summary causal ...

CUTS: Neural Causal Discovery from Irregular Time-Series Data

Causal discovery from time-series data has been a central task in machin...

Causal Discovery from Temporal Data: An Overview and New Perspectives

Temporal data, representing chronological observations of complex system...

Reconstructing regime-dependent causal relationships from observational time series

Inferring causal relations from observational time series data is a key ...

Code Repositories


Code for the paper: Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data

view repo


Experiments on Causal structure discovery and inference.

view repo