Deep learning of causal structures in high dimensions under data limitations

Nature Machine Intelligence, vol. 5, pp. 1306–1316

Abstract

Abstract Causal learning is a key challenge in scientific artificial intelligence as it allows researchers to go beyond purely correlative or predictive analyses towards learning underlying cause-and-effect relationships, which are important for scientific understanding as well as for a wide range of downstream tasks. Here, motivated by emerging biomedical questions, we propose a deep neural architecture for learning causal relationships between variables from a combination of high-dimensional data and prior causal knowledge. We combine convolutional and graph neural networks within a causal risk framework to provide an approach that is demonstrably effective under the conditions of high dimensionality, noise and data limitations that are characteristic of many applications, including in large-scale biology. In experiments, we find that the proposed learners can effectively identify novel causal relationships across thousands of variables. Results include extensive (linear and nonlinear) simulations (where the ground truth is known and can be directly compared against), as well as real biological examples where the models are applied to high-dimensional molecular data and their outputs compared against entirely unseen validation experiments. These results support the notion that deep learning approaches can be used to learn causal networks at large scale.

Authors 4

1. Kai Lagemann corresponding

   German Center for Neurodegenerative Diseases

   Affiliation as printed

   Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany

2. Christian Lagemann Aachen Institute of Aerodynamics

   RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics, RWTH Aachen University, Aachen, Germany

3. Bernd Taschler

   German Center for Neurodegenerative Diseases · University of Oxford

   Affiliation as printed

   Big Data Institute, Li Ka Shing Centre for Health Information and Discovery, University of Oxford, Oxford, UK

   Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany

4. Sach Mukherjee corresponding

   University of Cambridge · German Center for Neurodegenerative Diseases · MRC Biostatistics Unit

   Affiliation as printed

   MRC Biostatistics Unit, University of Cambridge, Cambridge, UK

   Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany