Riemannian Deep Learning: Modules, Networks, and Geometries

• URL: http://arxiv.org/abs/2607.19305v2
• Date: Wed, 22 Jul 2026 21:13:10 GMT
• Title: Riemannian Deep Learning: Modules, Networks, and Geometries
• Abstract summary: This thesis develops a unified framework for Riemannian deep learning from three complementary perspectives.<n>It generalizes batch normalization from Euclidean spaces to broad classes of Lie groups and gyrogroups.<n>It also develops neural networks for several important geometric representations, including hyperbolic space, Busemann-based hyperbolic learning, and full-rank correlation matrices.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific manifolds, rely on Euclidean approximations, or require costly and numerically fragile geometric operations. This thesis develops a unified framework for Riemannian deep learning from three complementary perspectives: reusable neural modules, manifold-specific network architectures, and the design of underlying geometries. It generalizes batch normalization from Euclidean spaces and individual manifolds to broad classes of Lie groups and gyrogroups, and extends multinomial logistic regression from Euclidean space to SPD manifolds and then to general Riemannian manifolds. It further develops neural networks for several important geometric representations, including an unconstrained model of hyperbolic space, Busemann-based hyperbolic learning, and full-rank correlation matrices. Finally, it introduces adaptive and computationally efficient Riemannian metrics on SPD manifolds, including learnable Log-Euclidean geometries and fast, stable Cholesky-based geometries. The proposed methods are supported by theoretical analysis and validated through numerical experiments and applications in vision, signal processing, graph learning, and genomics.

Related papers

• Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations [0.10152838128195464]
  This work provides a self-contained and rigorous treatment of the foundations of Riemannian geometry.<n>We develop the key geometric structures -- including tangent and cotangent spaces, tensor calculus, metric tensors, Levi-Civita connections, curvature, and geodesics.<n>We specialize these constructions to important matrix manifold, including the Stiefel, Grassmann, and SPD.
  arXiv  Detail & Related papers  (2026-05-04T07:11:11Z)
• ManifoldFormer: Geometric Deep Learning for Neural Dynamics on Riemannian Manifolds [11.275535457399625]
  Existing EEG foundation models mainly treat neural signals as generic time series in Euclidean space.<n>MandelaFormer addresses this limitation through a novel geometric deep learning framework that explicitly learns neural manifold representations.
  arXiv  Detail & Related papers  (2025-11-20T22:19:53Z)
• RMLR: Extending Multinomial Logistic Regression into General Geometries [64.16104856124029]
  Our framework only requires minimal geometric properties, thus exhibiting broad applicability. We develop five families of SPD MLRs under five types of power-deformed metrics. On rotation matrices we propose Lie MLR based on the popular bi-invariant metric.
  arXiv  Detail & Related papers  (2024-09-28T18:38:21Z)
• Matrix Manifold Neural Networks++ [18.385670036798707]
  We design fully-connected layers for SPD neural networks. We propose a method for performing backpropagation with the Grassmann logarithmic map in the projector perspective.
  arXiv  Detail & Related papers  (2024-05-29T15:47:35Z)
• 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)
• A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems [87.30652640973317]
  Recent advances in computational modelling of atomic systems represent them as geometric graphs with atoms embedded as nodes in 3D Euclidean space. Geometric Graph Neural Networks have emerged as the preferred machine learning architecture powering applications ranging from protein structure prediction to molecular simulations and material generation. This paper provides a comprehensive and self-contained overview of the field of Geometric GNNs for 3D atomic systems.
  arXiv  Detail & Related papers  (2023-12-12T18:44:19Z)
• 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)
• Adaptive Log-Euclidean Metrics for SPD Matrix Learning [73.12655932115881]
  We propose Adaptive Log-Euclidean Metrics (ALEMs), which extend the widely used Log-Euclidean Metric (LEM) The experimental and theoretical results demonstrate the merit of the proposed metrics in improving the performance of SPD neural networks.
  arXiv  Detail & Related papers  (2023-03-26T18:31:52Z)
• A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations [77.86290991564829]
  Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. We study a particular sequence of maps between manifold, with the last manifold of the sequence equipped with a Riemannian metric. We investigate the theoretical properties of the maps of such sequence, eventually we focus on the case of maps between implementing neural networks of practical interest.
  arXiv  Detail & Related papers  (2021-12-17T11:43:30Z)
• Semi-Riemannian Graph Convolutional Networks [36.09315878397234]
  We develop a principled Semi-Riemannian GCN that first models data in semi-Riemannian manifold of constant nonzero curvature. Our method provides a geometric inductive bias that is sufficiently flexible to model mixed heterogeneous topologies like hierarchical graphs with cycles.
  arXiv  Detail & Related papers  (2021-06-06T14:23:34Z)

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.