Sheaves Reloaded: A Direction Awakening

Stefano Fiorini, Hakan Aktas, Iulia Duta, Pietro Morerio, Alessio Del Bue, Pietro Lio, Stefano Coniglio

Keywords: directed sheaf neural network, directed graphs, directed cellular sheaves

Abstract:

Sheaf Neural Networks (SNNs) are a powerful algebraic-topology generalization of Graph Neural Networks (GNNs), and have been shown to significantly improve our ability to model complex relational data. While the GNN literature proved that incorporating directionality can substantially boost performance in many real-world applications, no SNNs approaches are known with such a capability. To address this limitation, we introduce the Directed Cellular Sheaf, a generalized cellular sheaf designed to explicitly account for edge orientations. Building on it, we define a corresponding sheaf Laplacian, the Directed Sheaf Laplacian $L^{\widetilde{\mathcal{F}}}$, which exploits the sheaf's structure to capture both the graph’s topology and its directions. $L^{\widetilde{\mathcal{F}}}$ 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 twelve real-world benchmarks show that DSNN consistently outperforms many baseline methods. The source
code can be found at https://github.com/hakanaktas0/DSNN.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 5143