Skip to main content
SHARE
Publication

Attention for Causal Relationship Discovery from Biological Neural Dynamics

Publication Type
Conference Paper
Book Title
NeuRIPS 2023 Workshop on Causal Representation Learning
Publication Date
Page Numbers
1 to 1
Conference Name
NeuRIPS 2023 Workshop on Causal Representation Learning
Conference Location
New Orleans, Louisiana, United States of America
Conference Sponsor
NeuRIPS
Conference Date
-

This paper explores the potential of the transformer models for learning Granger causality in networks with complex nonlinear dynamics at every node, as in neurobiological and biophysical networks. Our study primarily focuses on a proof-of-concept investigation based on simulated neural dynamics, for which the ground-truth causality is known through the underlying connectivity matrix. For transformer models trained to forecast neuronal population dynamics, we show that the cross-attention module effectively captures the causal relationship among neurons, with an accuracy equal to or superior to that of the most popular Granger causality discovery method. While we acknowledge that real-world neurobiology data will bring further challenges, including dynamic connectivity and unobserved variability, this research offers an encouraging preliminary glimpse into the utility of the transformer model for causal representation learning in neuroscience.