A Flow Matching Framework for Neural Representational Dissimilarity
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.
Related
- A hierarchical framework of representational emergence: From feature binding to supramodal emergence
- Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
- Decomposing deep neural network-brain representational similarity reveals distinct sources across the human visual hierarchy
- Assessing psychological, neural and AI-based representational geometries across multiple similarity properties
- Representational learning by optimization of neural manifolds in an olfactory memory network
BibTeX
@misc{ye2026flow,
title = {{A Flow Matching Framework for Neural Representational Dissimilarity}},
author = {Zeyuan Ye and Xue-Xin Wei},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.31544},
eprint = {2609.31544},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31544},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - A Flow Matching Framework for Neural Representational Dissimilarity
AU - Zeyuan Ye
AU - Xue-Xin Wei
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2609.31544
UR - https://arxiv.org/abs/2609.31544
AB - 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.
ER -