Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models

TL;DR

This paper introduces BeNeDiff, a novel method combining behavior-informed latent models and diffusion models to interpret neural dynamics related to behavior, enabling detailed exploration of neural representations in widefield calcium imaging data.

Contribution

We develop BeNeDiff, a new approach that disentangles neural subspaces and synthesizes behavior videos to interpret neural dynamics, addressing limitations of existing decoding models.

Findings

Neural subspace in BeNeDiff is highly disentangled.

Diffusion models successfully synthesize behavior videos from neural data.

Method provides interpretable neural-behavior relationships.

Abstract

Understanding the neural basis of behavior is a fundamental goal in neuroscience. Current research in large-scale neuro-behavioral data analysis often relies on decoding models, which quantify behavioral information in neural data but lack details on behavior encoding. This raises an intriguing scientific question: ``how can we enable in-depth exploration of neural representations in behavioral tasks, revealing interpretable neural dynamics associated with behaviors''. However, addressing this issue is challenging due to the varied behavioral encoding across different brain regions and mixed selectivity at the population level. To tackle this limitation, our approach, named ``BeNeDiff'', first identifies a fine-grained and disentangled neural subspace using a behavior-informed latent variable model. It then employs state-of-the-art generative diffusion models to synthesize behavior videos that interpret the neural dynamics of each latent factor. We validate the method on multi-session datasets containing widefield calcium imaging recordings across the dorsal cortex. Through guiding the diffusion model to activate individual latent factors, we verify that the neural dynamics of latent factors in the disentangled neural subspace provide interpretable quantifications of the behaviors of interest. At the same time, the neural subspace in BeNeDiff demonstrates high disentanglement and neural reconstruction quality.