Stimulus symmetries can confound representational similarity analyses

• URL: http://arxiv.org/abs/2605.21324v1
• Date: Wed, 20 May 2026 15:51:21 GMT
• Title: Stimulus symmetries can confound representational similarity analyses
• Abstract summary: We show that symmetries in network inputs can confound RSM-based analyses.<n>We show that these phenomena are present in networks trained to encode image data, where the symmetry is latent.
• Score: 8.064168190307209
• License: http://creativecommons.org/licenses/by/4.0/
• 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. 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 papers

• Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning [52.26396748560348]
  We provide an overview of high dimensional dynamical systems driven by random matrices.<n>We focus on applications to simple models of learning and generalization in machine learning theory.
  arXiv  Detail & Related papers  (2026-01-03T00:12:32Z)
• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• Dynamical similarity analysis can identify compositional dynamics developing in RNNs [3.037387520023979]
  compositional learning in neural networks (RNNs) allows us to build a test case for dynamical representation alignment metrics.<n>We show that the new Dynamical Similarity Analysis (DSA) is more noise robust and identifies behaviorally relevant representations more reliably than prior metrics.
  arXiv  Detail & Related papers  (2024-10-31T16:07:21Z)
• The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof [50.49582712378289]
  We investigate the impact of neural parameter symmetries by introducing new neural network architectures. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries.
  arXiv  Detail & Related papers  (2024-05-30T16:32:31Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Symmetry Induces Structure and Constraint of Learning [0.0]
  We unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine learning models. Common instances of mirror symmetries in deep learning include rescaling, rotation, and permutation symmetry. We show that the theoretical framework can explain intriguing phenomena, such as the loss of plasticity and various collapse phenomena in neural networks.
  arXiv  Detail & Related papers  (2023-09-29T02:21:31Z)
• Unsupervised Learning of Invariance Transformations [105.54048699217668]
  We develop an algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.
  arXiv  Detail & Related papers  (2023-07-24T17:03:28Z)
• Hidden symmetries of ReLU networks [17.332539115959708]
  In some networks, the only symmetries are permutation of neurons in a layer and positive scaling of parameters at a neuron, while other networks admit additional hidden symmetries. In this work, we prove that, for any network architecture where no layer is narrower than the input, there exist parameter settings with no hidden symmetries.
  arXiv  Detail & Related papers  (2023-06-09T18:07:06Z)
• Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations [0.0]
  We present a method of automatically detecting RL symmetries directly from raw trajectory data without requiring active control of the system. We show in experiments on two simulated RL use cases that our method can determine the symmetries underlying both the environment physics and the trained RL policy.
  arXiv  Detail & Related papers  (2022-11-29T17:00:26Z)
• Deep Representational Similarity Learning for analyzing neural signatures in task-based fMRI dataset [81.02949933048332]
  This paper develops Deep Representational Similarity Learning (DRSL), a deep extension of Representational Similarity Analysis (RSA) DRSL is appropriate for analyzing similarities between various cognitive tasks in fMRI datasets with a large number of subjects.
  arXiv  Detail & Related papers  (2020-09-28T18:30:14Z)
• Detecting Symmetries with Neural Networks [0.0]
  We make extensive use of the structure in the embedding layer of the neural network. We identify whether a symmetry is present and to identify orbits of the symmetry in the input. For this example we present a novel data representation in terms of graphs.
  arXiv  Detail & Related papers  (2020-03-30T17:58:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.