TAVRNN: Temporal Attention-enhanced Variational Graph RNN Captures Neuronal Dynamics and Behavior

Moein Khajehnejad, Forough Habibollahi, Ahmad Khajehnejad, Brett Joseph Kagan, Adeel Razi

Keywords: Representation Learning, Attention, Graph Recurrent Neuronal Network, Neuronal Dynamics, Electrophysiology, Calcium Imaging, Behaviour

TL;DR: TAVRNN Links Neuronal Dynamics and Behavior

Abstract:

We introduce Temporal Attention-enhanced Variational Graph Recurrent Neural Network (TAVRNN), a novel framework for analyzing the evolving dynamics of neuronal connectivity networks in response to external stimuli and behavioral feedback. TAVRNN captures temporal changes in network structure by modeling sequential snapshots of neuronal activity, enabling the identification of key connectivity patterns. Leveraging temporal attention mechanisms and variational graph techniques, TAVRNN uncovers how connectivity shifts align with behavior over time. We validate TAVRNN on two datasets: _in vivo_ calcium imaging data from freely behaving rats and novel _in vitro_ electrophysiological data from the _DishBrain_ system, where biological neurons control a simulated environment during the game of _pong_. We show that TAVRNN outperforms previous baseline models in classification, clustering tasks and computational efficiency while accurately linking connectivity changes to performance variations. Crucially, TAVRNN reveals that high game performance in the _DishBrain_ system correlates with the alignment of sensory and motor subregion channels, a relationship not evident in earlier models.
This framework represents the first application of dynamic graph representation of electrophysiological (neuronal) data from _DishBrain_ system, providing insights into the reorganization of neuronal networks during learning. TAVRNN’s ability to differentiate between neuronal states associated with successful and unsuccessful learning outcomes, offers significant implications for real-time monitoring and manipulation of biological neuronal systems.

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5299