paper-with-me

Papers

Gaussian Sheaf Neural Networks

2026-05-20 · André Ribeiro, Ana Luiza Tenório, Tiago da Silva, Diego Mesquita arxiv

Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited for vector-valued node features, there are cases in which node features are better represented by probability distributions than real vectors. Concretely, when node features are Gaussians, characterized by a mean and a covariance matrix, naively concatenating their parameters into a single vector and applying standard message passing discards the geometric and algebraic structure that governs means and covariances. We propose Gaussian Sheaf Neural Networks (GSNNs), a principled framework that incorporates these inductive biases into graph-based learning. Building on the theory of cellular sheaves, we derive a new Laplacian operator that generalizes the sheaf Laplacian to this setting and preserves its key properties. We complement our theoretical contributions with experiments on synthetic and real-world data that illustrate the practical relevance of GSNNs.

📄 PDF Abstract BibTeX arXiv:2605.21435

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian Sheaf Neural Networks

2024-10-12 · Patrick Gillespie, Vasileios Maroulas, Ioannis Schizas

Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constr…

Demystifying Oversmoothing in Sheaf Neural Networks: An Index-Theoretic Criterion

2026-08-17 · Junwen Dong, Yuhan Peng, Hao Li, Huitao Feng 외 arxiv

To combat oversmoothing in Graph Convolutional Networks, Sheaf Neural Networks (SNNs) were proposed as a generalization by equipping the graph with a sheaf structure and replacing the graph Laplacian with a sheaf Laplaci…

On the Necessity of Learnable Sheaf Laplacians

2026-03-05 · Ferran Hernandez Caralt, Mar Gonzàlez i Català, Adrián Bazaga, Pietro Liò arxiv

Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input graph and replacing the adjacency-based oper…

Hierarchical Pooling for Sheaf Neural Networks

2026-06-18 · Dionisia Naddeo, Carlo Abate, Pietro Liò, Nicola Toschi 외 arxiv

Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibility across edges. Unlike standard graph d…

Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves

2025-11-28 · Alessio Borgi, Fabrizio Silvestri, Pietro Liò arxiv

Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-…