English

Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back

Signal Processing 2024-03-19 v2 Machine Learning

Abstract

In this work we introduce a convolution operation over the tangent bundle of Riemann manifolds in terms of exponentials of the Connection Laplacian operator. We define tangent bundle filters and tangent bundle neural networks (TNNs) based on this convolution operation, which are novel continuous architectures operating on tangent bundle signals, i.e. vector fields over the manifolds. Tangent bundle filters admit a spectral representation that generalizes the ones of scalar manifold filters, graph filters and standard convolutional filters in continuous time. We then introduce a discretization procedure, both in the space and time domains, to make TNNs implementable, showing that their discrete counterpart is a novel principled variant of the very recently introduced sheaf neural networks. We formally prove that this discretized architecture converges to the underlying continuous TNN. Finally, we numerically evaluate the effectiveness of the proposed architecture on various learning tasks, both on synthetic and real data.

Keywords

Cite

@article{arxiv.2303.11323,
  title  = {Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back},
  author = {Claudio Battiloro and Zhiyang Wang and Hans Riess and Paolo Di Lorenzo and Alejandro Ribeiro},
  journal= {arXiv preprint arXiv:2303.11323},
  year   = {2024}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2210.15058

R2 v1 2026-06-28T09:24:46.441Z