Stimulus symmetries can confound representational similarity analyses
Abstract
What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the need for a more complete characterization of their properties. Here, we show that symmetries in network inputs can confound RSM-based analyses. Stimulus symmetries render many representations functionally equivalent, but these different configurations can lead to different RSMs. These different RSMs reflect qualitatively different representational geometries, ranging from disentangled to maximally-mixed codes. We show that stochastic gradient descent or energetic regularization can generate sparse, drifting codes, leading in turn to drifting RSMs. Moreover, we demonstrate that these phenomena are present in networks trained to encode image data, where the symmetry is latent. Our results illustrate the challenges inherent in comparing nonlinear neural codes, when functionally-equivalent representations are not related by a simple rotation.
Related
- COMPASS 2.0: psychometric representational similarity analysis distinguishes symptom structure from personal signal
- Multidimensional semantic representations emerge from multi-frequency representational similarity learning
- 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
BibTeX
@misc{pashakhanloo2026stimulus,
title = {{Stimulus symmetries can confound representational similarity analyses}},
author = {Farhad Pashakhanloo and Jacob A. Zavatone-Veth},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.21324},
eprint = {2605.21324},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.21324},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Stimulus symmetries can confound representational similarity analyses
AU - Farhad Pashakhanloo
AU - Jacob A. Zavatone-Veth
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2605.21324
UR - https://arxiv.org/abs/2605.21324
AB - What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the need for a more complete characterization of their properties. Here, we show that symmetries in network inputs can confound RSM-based analyses. Stimulus symmetries render many representations functionally equivalent, but these different configurations can lead to different RSMs. These different RSMs reflect qualitatively different representational geometries, ranging from disentangled to maximally-mixed codes. We show that stochastic gradient descent or energetic regularization can generate sparse, drifting codes, leading in turn to drifting RSMs. Moreover, we demonstrate that these phenomena are present in networks trained to encode image data, where the symmetry is latent. Our results illustrate the challenges inherent in comparing nonlinear neural codes, when functionally-equivalent representations are not related by a simple rotation.
ER -