English

MagNet: A Neural Network for Directed Graphs

Machine Learning 2021-06-14 v2

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.

Keywords

Cite

@article{arxiv.2102.11391,
  title  = {MagNet: A Neural Network for Directed Graphs},
  author = {Xitong Zhang and Yixuan He and Nathan Brugnone and Michael Perlmutter and Matthew Hirn},
  journal= {arXiv preprint arXiv:2102.11391},
  year   = {2021}
}

Comments

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

R2 v1 2026-06-23T23:25:21.251Z