MagNet: A Neural Network for Directed Graphs

Abstract

The prevalence of graph-based data has spurred the rapid development of graph neural networks (GNNs) and related machine learning algorithms. Yet, despite the many datasets naturally modeled as directed graphs, including citation, website, and traffic networks, the vast majority of this research focuses on undirected graphs. In this paper, we propose MagNet, a spectral GNN for directed graphs based on a complex Hermitian matrix known as the magnetic Laplacian. This matrix encodes undirected geometric structure in the magnitude of its entries and directional information in their phase. A "charge" parameter attunes spectral information to variation among directed cycles. We apply our network to a variety of directed graph node classification and link prediction tasks showing that MagNet performs well on all tasks and that its performance exceeds all other methods on a majority of such tasks. The underlying principles of MagNet are such that it can be adapted to other spectral GNN architectures.

22 pages, 4 figures, 15 tables. v2: Numerous revisions to the paper's content, including: a more general and informative presentation; many new numerical experiments; revised figures

References in corpus (9)

• Inductive Representation Learning on Large Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Higher-order organization of complex networks
• How Powerful are Graph Neural Networks?
• Geom-GCN: Geometric Graph Convolutional Networks
• Directed Graph Convolutional Network
• Magnetic eigenmaps for community detection in directed networks
• Spectral-based Graph Convolutional Network for Directed Graphs
• Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks

Cited by in corpus (5)

• Dirac signal processing of higher-order topological signals
• Higher-order Connection Laplacians for Directed Simplicial Complexes
• LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks
• FLEE-GNN: A Federated Learning System for Edge-Enhanced Graph Neural Network in Analyzing Geospatial Resilience of Multicommodity Food Flows
• An iterative spectral algorithm for digraph clustering