Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds

• URL: http://arxiv.org/abs/2603.28764v1
• Date: Mon, 30 Mar 2026 17:59:22 GMT
• Title: Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds
• Abstract summary: Similarity measures are widely used to interpret the representational geometries used by neural networks to solve tasks.<n>Here, we introduce metric similarity analysis (MSA), a novel method to compare the intrinsic geometry of neural representations under the manifold hypothesis.
• Score: 2.2917707112773598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Similarity measures are widely used to interpret the representational geometries used by neural networks to solve tasks. Yet, because existing methods compare the extrinsic geometry of representations in state space, rather than their intrinsic geometry, they may fail to capture subtle yet crucial distinctions between fundamentally different neural network solutions. Here, we introduce metric similarity analysis (MSA), a novel method which leverages tools from Riemannian geometry to compare the intrinsic geometry of neural representations under the manifold hypothesis. We show that MSA can be used to i) disentangle features of neural computations in deep networks with different learning regimes, ii) compare nonlinear dynamics, and iii) investigate diffusion models. Hence, we introduce a mathematically grounded and broadly applicable framework to understand the mechanisms behind neural computations by comparing their intrinsic geometries.

Related papers

• Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks [0.0]
  We develop order-equivariant neural networks (OENN), which generalize standard graph message passing and sheaf neural networks.<n>We show that OENN can be extended further to CENN, which gives the general form of equivariant neural networks.
  arXiv  Detail & Related papers  (2026-07-04T09:59:11Z)
• Riemannian Geometry for the classification of brain states with intracortical brain-computer interfaces [3.0026377736031846]
  We propose a new method for brain decoding using invasive electrophysiological recordings.<n>The method achieves a superior mean F1 macro-averaged score across different channel configurations.<n>The geometric framework reveals distinct spatial contributions of brain regions across varying brain states.
  arXiv  Detail & Related papers  (2025-04-07T22:11:59Z)
• Scalable Geometric Learning with Correlation-Based Functional Brain Networks [0.0]
  The correlation matrix is a central representation of functional brain networks in neuroimaging.<n>Traditional analyses often treat pairwise interactions independently in a Euclidean setting.<n>This paper presents a novel geometric framework that embeds correlation matrices into a Euclidean space.
  arXiv  Detail & Related papers  (2025-03-31T01:35:50Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• A singular Riemannian Geometry Approach to Deep Neural Networks III. Piecewise Differentiable Layers and Random Walks on $n$-dimensional Classes [49.32130498861987]
  We study the case of non-differentiable activation functions, such as ReLU. Two recent works introduced a geometric framework to study neural networks. We illustrate our findings with some numerical experiments on classification of images and thermodynamic problems.
  arXiv  Detail & Related papers  (2024-04-09T08:11:46Z)
• Riemannian Residual Neural Networks [58.925132597945634]
  We show how to extend the residual neural network (ResNet) ResNets have become ubiquitous in machine learning due to their beneficial learning properties, excellent empirical results, and easy-to-incorporate nature when building varied neural networks.
  arXiv  Detail & Related papers  (2023-10-16T02:12:32Z)
• Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis [7.660368798066376]
  We introduce a novel similarity metric that compares two systems at the level of their dynamics. Our method opens the door to comparative analyses of the essential temporal structure of computation in neural circuits.
  arXiv  Detail & Related papers  (2023-06-16T20:11:38Z)
• Interpretable statistical representations of neural population dynamics and geometry [4.459704414303749]
  We introduce a representation learning method, MARBLE, that decomposes on-manifold dynamics into local flow fields and maps them into a common latent space. In simulated non-linear dynamical systems, recurrent neural networks, and experimental single-neuron recordings from primates and rodents, we discover emergent low-dimensional latent representations. These representations are consistent across neural networks and animals, enabling the robust comparison of cognitive computations.
  arXiv  Detail & Related papers  (2023-04-06T21:11:04Z)
• Representational dissimilarity metric spaces for stochastic neural networks [4.229248343585332]
  Quantifying similarity between neural representations is a perennial problem in deep learning and neuroscience research. We generalize shape metrics to quantify differences in representations. We find that neurobiological oriented visual gratings and naturalistic scenes respectively resemble untrained and trained deep network representations.
  arXiv  Detail & Related papers  (2022-11-21T17:32:40Z)
• Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty [91.0564497403256]
  We present a novel framework that involves probabilistic fusion between the two families of predictions during network training. Our network features a self-attention graph neural network, which drives the learning by enforcing strong interactions between different correspondences. We propose motion parmeterizations suitable for learning and show that our method achieves state-of-the-art performance on the challenging DeMoN and ScanNet datasets.
  arXiv  Detail & Related papers  (2021-04-16T17:59:06Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

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.