A Flow Matching Framework for Neural Representational Dissimilarity

2026-09-25

AI Summary

This study addresses the challenge of estimating neural representational distance metrics under complex distributions and the absence of systematic design principles for novel metrics. To this end, this work introduces flow matching from generative modeling into neuroscience for the first time, establishing a unified theoretical framework. By leveraging deep generative models and velocity field constrained optimization, the proposed framework formulates diverse distance metrics as Jeffreys divergences under distinct velocity constraints, thereby enabling efficient processing of continuous variables and complex distributions. This approach significantly improves distance estimation accuracy in complex distributional settings, provides a systematic paradigm for designing new metrics, and advances our understanding of differences in neural coding.

Abstract

Neural representational dissimilarity quantifies differences between neural response distributions, and is essential for comparing neural codes across stimuli, brain areas, tasks, and models. Commonly used distance metrics involve different assumptions and are estimated with separate methods. Here, we show that a variety of distance metrics can be unified under a flow matching framework developed in deep generative models. That is, these distances arise as Jeffreys divergences under different velocity constraints. We find that flow matching has advantages for estimating distances involving complicated distributions and continuous variables. Furthermore, this framework enables the design of new distance metrics in a principled way. Together, flow matching provides a unified approach for understanding, estimating, and designing neural representational dissimilarity metrics.

Problem

• neural representational dissimilarity
• distance metrics
• flow matching
• Jeffreys divergence

Innovation

• Flow Matching
• Neural Representational Dissimilarity
• Jeffreys Divergence
• Distance Metrics
• Deep Generative Models