English
Related papers

Related papers: Sheaf Hypergraph Networks

200 papers

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 constructing the sheaf is…

Machine Learning · Computer Science 2025-09-15 Patrick Gillespie , Layal Bou Hamdan , Ioannis Schizas , David L. Boothe , Vasileios Maroulas

Graph-based signal processing techniques have become essential for handling data in non-Euclidean spaces. However, there is a growing awareness that these graph models might need to be expanded into `higher-order' domains to effectively…

Machine Learning · Computer Science 2024-04-15 Mustafa Hajij , Ghada Zamzmi , Theodore Papamarkou , Aldo Guzmán-Sáenz , Tolga Birdal , Michael T. Schaub

Recently various types of topological Laplacians have been studied from the perspective of data analysis. The spectral theory of these Laplacians has significantly extended the scope of algebraic topology and data analysis. Inspired by the…

Algebraic Topology · Mathematics 2023-12-06 Xiaoqi Wei , Guo-Wei Wei

This work focuses on exploring the potential benefits of introducing a nonlinear Laplacian in Sheaf Neural Networks for graph-related tasks. The primary aim is to understand the impact of such nonlinearity on diffusion dynamics, signal…

Machine Learning · Computer Science 2024-03-04 Olga Zaghen

Hypergraphs are useful mathematical models for describing complex relationships among members of a structured graph, while hyperdigraphs serve as a generalization that can encode asymmetric relationships in the data. However, obtaining…

Algebraic Topology · Mathematics 2023-04-10 Dong Chen , Jian Liu , Jie Wu , Guo-Wei Wei

Over the recent years, Graph Neural Networks have become increasingly popular in network analytic and beyond. With that, their architecture noticeable diverges from the classical multi-layered hierarchical organization of the traditional…

Machine Learning · Computer Science 2021-05-17 Stanislav Sobolevsky

Graph hypernetworks (GHNs), constructed by combining graph neural networks (GNNs) with hypernetworks (HNs), leverage relational data across various domains such as neural architecture search, molecular property prediction and federated…

Machine Learning · Computer Science 2024-06-03 Bao Nguyen , Lorenzo Sani , Xinchi Qiu , Pietro Liò , Nicholas D. Lane

Hypergraphs extend traditional graphs by enabling the representation of N-ary relationships through higher-order edges. Akin to a common approach of deriving graph Laplacians, we define function spaces and corresponding symmetric products…

Differential Geometry · Mathematics 2026-03-27 Jo Andersson Stokke , Ronny Bergmann , Martin Hanik , Christoph von Tycowicz

In data science, hypergraphs are natural models for data exhibiting multi-way relations, whereas graphs only capture pairwise. Nonetheless, many proposed hypergraph neural networks effectively reduce hypergraphs to undirected graphs via…

Machine Learning · Computer Science 2025-04-18 Tatyana Benko , Martin Buck , Ilya Amburg , Stephen J. Young , Sinan G. Aksoy

A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear maps between these spaces. SNNs have been shown to have…

Many real-world phenomena are naturally modeled by graphs and networks. However, classical graph models are often limited to pairwise interactions and may not adequately capture the richer structures that arise in practice. Higher-order…

Social and Information Networks · Computer Science 2026-05-18 Takaaki Fujita , Florentin Smarandache

Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields. Most of those algorithms have assumed pairwise relationships of objects of interest. However, in many real…

Machine Learning · Computer Science 2020-10-13 Song Bai , Feihu Zhang , Philip H. S. Torr

Graphs are the most ubiquitous form of structured data representation used in machine learning. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations found in many real-world…

Machine Learning · Computer Science 2020-10-12 Devanshu Arya , Deepak K. Gupta , Stevan Rudinac , Marcel Worring

This paper provides an overview of the applications of sheaf theory in deep learning, data science, and computer science in general. The primary text of this work serves as a friendly introduction to applied and computational sheaf theory…

Algebraic Topology · Mathematics 2025-02-24 Anton Ayzenberg , Thomas Gebhart , German Magai , Grigory Solomadin

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities. Hypergraph neural networks emerge as a powerful tool for processing hypergraph-structured data, delivering…

Machine Learning · Computer Science 2024-06-04 Zexi Liu , Bohan Tang , Ziyuan Ye , Xiaowen Dong , Siheng Chen , Yanfeng Wang

Graph representation learning has made major strides over the past decade. However, in many relational domains, the input data are not suited for simple graph representations as the relationships between entities go beyond pairwise…

Machine Learning · Computer Science 2021-01-20 Balasubramaniam Srinivasan , Da Zheng , George Karypis

Complex systems are often driven by higher-order interactions among multiple units, naturally represented as hypergraphs. Understanding dependency structures within these hypergraphs is crucial for understanding and predicting the behavior…

Social and Information Networks · Computer Science 2025-05-29 John Hood , Caterina De Bacco , Aaron Schein

Many empirical systems contain complex interactions of arbitrary size, representing, for example, chemical reactions, social groups, co-authorship relationships, and ecological dependencies. These interactions are known as higher-order…

Complex systems, such as economic, social, biological, and ecological systems, usually feature interactions not only between pairwise entities but also among three or more entities. These multi-entity interactions are known as higher-order…

Physics and Society · Physics 2025-06-06 Junhap Bian , Tao Zhou , Yilin Bi

Sheaf Neural Networks (SNNs) naturally extend Graph Neural Networks (GNNs) by endowing a cellular sheaf over the graph, equipping nodes and edges with vector spaces and defining linear mappings between them. While the attached geometric…

Machine Learning · Computer Science 2024-07-31 Ferran Hernandez Caralt , Guillermo Bernárdez Gil , Iulia Duta , Pietro Liò , Eduard Alarcón Cot