Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917614787231744 |
|---|---|
| author | Battiloro, Claudio Wang, Zhiyang Riess, Hans Di Lorenzo, Paolo Ribeiro, Alejandro |
| author_facet | Battiloro, Claudio Wang, Zhiyang Riess, Hans Di Lorenzo, Paolo Ribeiro, Alejandro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_11323 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back Battiloro, Claudio Wang, Zhiyang Riess, Hans Di Lorenzo, Paolo Ribeiro, Alejandro Signal Processing Machine Learning 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. |
| title | Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2303.11323 |