Paper Image

Learning neural Granger causality with a single model

Published on:

14 May 2024

Primary Category:

Machine Learning

Paper Authors:

Wanqi Zhou,

Shuanghao Bai,

Shujian Yu,

Qibin Zhao,

Badong Chen


Key Details

Proposes novel single-model framework for neural Granger causality

Regularizes input-output Jacobian to constrain causality

Achieves state-of-the-art performance for summary and full-time causality

Lower model complexity than existing methods

Scalable to high-dimensional multivariate time series

AI generated summary

Learning neural Granger causality with a single model

This paper proposes a new method to identify causal relationships between time series variables using a single neural network model. By regularizing the input-output Jacobian matrix, the method eliminates issues with relying on weight sparsity and separate models per variable. It demonstrates high performance and scalability in capturing both multivariate and temporal causal effects on benchmark datasets.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up