Gauge Freedom and Metric Dependence in Neural Representation Spaces

• URL: http://arxiv.org/abs/2603.06774v1
• Date: Fri, 06 Mar 2026 17:54:22 GMT
• Title: Gauge Freedom and Metric Dependence in Neural Representation Spaces
• Abstract summary: We study neural representation spaces as vector spaces with a gauge freedom under the general linear group.<n>We show that cosine similarity measures such as cosine similarity become metric-dependent quantities.<n>Experiments on multilayer perceptrons and convolutional networks confirm that inserting invertible transformations into trained models can substantially distort cosine similarity and nearest-neighbor structure.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural network representations are often analyzed as vectors in a fixed Euclidean space. However, their coordinates are not uniquely defined. If a hidden representation is transformed by an invertible linear map, the network function can be preserved by applying the inverse transformation to downstream weights. Representations are therefore defined only up to invertible linear transformations. We study neural representation spaces from this geometric viewpoint and treat them as vector spaces with a gauge freedom under the general linear group. Within this framework, commonly used similarity measures such as cosine similarity become metric-dependent quantities whose values can change under coordinate transformations that leave the model function unchanged. This provides a common interpretation for several observations in the literature, including cosine-similarity instability, anisotropy in embedding spaces, and the appeal of representation comparison methods such as SVCCA and CKA. Experiments on multilayer perceptrons and convolutional networks confirm that inserting invertible transformations into trained models can substantially distort cosine similarity and nearest-neighbor structure while leaving predictions unchanged. These results indicate that analysis of neural representations should focus either on quantities that are invariant under this gauge freedom or on explicitly chosen canonical coordinates.

Related papers

• Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs [21.112518373064486]
  Equivariant graph neural networks provide principled way to model geometric systems.<n>We introduce textscESNN, an Equivariant Sheaf Neural Network that learns directed, matrix-valued transport between neighboring vector features.<n>We show that learning how geometric information is transported across edges offers a complementary route to expressive equivariant message passing.
  arXiv  Detail & Related papers  (2026-08-28T20:49:43Z)
• Fubini Study geometry of representation drift in high dimensional data [0.0]
  High dimensional representation drift is commonly quantified using Euclidean or cosine distances.<n>We introduce a projective geometric view of representation drift grounded in the Fubini Study metric.<n>We show that the Fubini Study metric isolates intrinsic evolution by remaining invariant under gauge-induced fluctuations.
  arXiv  Detail & Related papers  (2026-02-01T16:00:59Z)
• Gauge-invariant representation holonomy [1.078600700827543]
  Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness.<n>Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation sets, but miss how representations change along input paths.<n>We introduce representation holonomy, a gauge-invariant statistic that measures this path dependence.
  arXiv  Detail & Related papers  (2026-01-29T12:51:17Z)
• 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)
• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• EqNIO: Subequivariant Neural Inertial Odometry [33.96552018734359]
  We show that IMU data transforms equivariantly, when rotated around the gravity vector and reflected with respect to arbitrary planes parallel to gravity. We then map the IMU data into this frame, thereby achieving an invariant canonicalization that can be directly used with off-the-shelf inertial odometry networks.
  arXiv  Detail & Related papers  (2024-08-12T17:42:46Z)
• Optimization Dynamics of Equivariant and Augmented Neural Networks [2.7918308693131135]
  We investigate the optimization of neural networks on symmetric data. We compare the strategy of constraining the architecture to be equivariant to that of using data augmentation. Our analysis reveals that even in the latter situation, stationary points may be unstable for augmented training although they are stable for the manifestly equivariant models.
  arXiv  Detail & Related papers  (2023-03-23T17:26:12Z)
• Revisiting Transformation Invariant Geometric Deep Learning: An Initial Representation Perspective [38.314914702299056]
  We propose Transformation In Neural Networks (TinvNN), a straightforward and general plug-in for geometric data.<n>Specifically, we realize transformation invariant and distance-preserving initial point representations by modifying multi-dimensional scaling.<n>We prove that TinvNN can strictly guarantee transformation invariant, being general and flexible enough to be combined with the existing neural networks.
  arXiv  Detail & Related papers  (2021-12-23T03:52:33Z)
• Tensor Component Analysis for Interpreting the Latent Space of GANs [41.020230946351816]
  This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) Our scheme allows for both linear edits corresponding to the individual modes of the tensor, and non-linear ones that model the multiplicative interactions between them. We show experimentally that we can utilise the former to better separate style- from geometry-based transformations, and the latter to generate an extended set of possible transformations.
  arXiv  Detail & Related papers  (2021-11-23T09:14:39Z)
• Topographic VAEs learn Equivariant Capsules [84.33745072274942]
  We introduce the Topographic VAE: a novel method for efficiently training deep generative models with topographically organized latent variables. We show that such a model indeed learns to organize its activations according to salient characteristics such as digit class, width, and style on MNIST. We demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
  arXiv  Detail & Related papers  (2021-09-03T09:25:57Z)
• Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization [80.55951673479237]
  We propose a novel invariant deep compressible covariance pooling (IDCCP) to solve nuisance variations in aerial scene categorization. We conduct extensive experiments on the publicly released aerial scene image data sets and demonstrate the superiority of this method compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-11T11:13:07Z)
• Learning Disentangled Representations with Latent Variation Predictability [102.4163768995288]
  This paper defines the variation predictability of latent disentangled representations. Within an adversarial generation process, we encourage variation predictability by maximizing the mutual information between latent variations and corresponding image pairs. We develop an evaluation metric that does not rely on the ground-truth generative factors to measure the disentanglement of latent representations.
  arXiv  Detail & Related papers  (2020-07-25T08:54:26Z)

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.