Sheaves Reloaded: A Directional Awakening
By: Stefano Fiorini , Hakan Aktas , Iulia Duta and more
Potential Business Impact:
Makes computers understand data with directions better.
Sheaf Neural Networks (SNNs) represent a powerful generalization of Graph Neural Networks (GNNs) that significantly improve our ability to model complex relational data. While directionality has been shown to substantially boost performance in graph learning tasks and is key to many real-world applications, existing SNNs fall short in representing it. To address this limitation, we introduce the Directed Cellular Sheaf, a special type of cellular sheaf designed to explicitly account for edge orientation. Building on this structure, we define a new sheaf Laplacian, the Directed Sheaf Laplacian, which captures both the graph's topology and its directional information. This operator serves as the backbone of the Directed Sheaf Neural Network (DSNN), the first SNN model to embed a directional bias into its architecture. Extensive experiments on nine real-world benchmarks show that DSNN consistently outperforms baseline methods.
Similar Papers
Cooperative Sheaf Neural Networks
Machine Learning (CS)
Lets computers learn from messy, connected information.
Asynchronous Nonlinear Sheaf Diffusion for Multi-Agent Coordination
Optimization and Control
Helps robots work together even with delays.
Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
Machine Learning (CS)
Helps computers understand complex connections better.