A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and
applications, and thus investigation of deep learning for HOIs has become a valuable …
applications, and thus investigation of deep learning for HOIs has become a valuable …
Differentiable Euler characteristic transforms for shape classification
E Roell, B Rieck - arXiv preprint arXiv:2310.07630, 2023 - arxiv.org
The Euler Characteristic Transform (ECT) has proven to be a powerful representation,
combining geometrical and topological characteristics of shapes and graphs. However, the …
combining geometrical and topological characteristics of shapes and graphs. However, the …
E (n) Equivariant Topological Neural Networks
C Battiloro, E Karaismailoğlu, M Tec… - arXiv preprint arXiv …, 2024 - arxiv.org
Graph neural networks excel at modeling pairwise interactions, but they cannot flexibly
accommodate higher-order interactions and features. Topological deep learning (TDL) has …
accommodate higher-order interactions and features. Topological deep learning (TDL) has …
Attending to Topological Spaces: The Cellular Transformer
R Ballester, P Hernández-García, M Papillon… - arXiv preprint arXiv …, 2024 - arxiv.org
Topological Deep Learning seeks to enhance the predictive performance of neural network
models by harnessing topological structures in input data. Topological neural networks …
models by harnessing topological structures in input data. Topological neural networks …
Cellular Cosheaves, Graphic Statics, and Mechanics
Z Cooperband - 2024 - repository.upenn.edu
This dissertation develops cellular cosheaf theory for the analysis of physical structures. This
approach generalizes well known linear matrix methods to cosheaf homology. The core …
approach generalizes well known linear matrix methods to cosheaf homology. The core …