paper-with-me

Papers

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

2023-03-20 · Claudio Battiloro, Zhiyang Wang, Hans Riess, Paolo Di Lorenzo, Alejandro Ribeiro

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.

📄 PDF Abstract BibTeX arXiv:2303.11323

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Back

2022-10-26 · Claudio Battiloro, Zhiyang Wang, Hans Riess, Paolo Di Lorenzo 외

In this work we introduce a convolution operation over the tangent bundle of Riemannian manifolds exploiting the Connection Laplacian operator. We use the convolution to define tangent bundle filters and tangent bundle n…

Denoising

Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

2026-05-07 · Kartik Tandon, Julian Gould, Tanishq Bhatia, Francesca Dominici 외 arxiv

Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operators, and are defined over irregular doma…

Riemannian Geometry with differentiable ambient space and metric operator

2021-05-04 · Du Nguyen

We show Riemannian geometry could be studied by identifying the tangent bundle of a Riemannian manifold $\mathcal{M}$ with a subbundle of the trivial bundle $\mathcal{M} \times \mathcal{E}$, obtained by embedding $\mathc…

Embedding Riemannian Manifolds by the Heat Kernel of the Connection Laplacian

2013-05-18 · Hau-Tieng Wu

Given a class of closed Riemannian manifolds with prescribed geometric conditions, we introduce an embedding of the manifolds into $\ell^2$ based on the heat kernel of the Connection Laplacian associated with the Levi-Ci…

Complex Functional Maps : a Conformal Link Between Tangent Bundles

2021-12-17 · Nicolas Donati, Etienne Corman, Simone Melzi, Maks Ovsjanikov

In this paper, we introduce complex functional maps, which extend the functional map framework to conformal maps between tangent vector fields on surfaces. A key property of these maps is their orientation awareness. Mor…