TY - CHAP
T1 - MagNet: A Neural Network for Directed Graphs
AU - Zhang, Xitong
AU - He, Yixuan
AU - Brugnone, Nathan
AU - Perlmutter, Michael
AU - Hirn, Matthew
N1 - MagNet: A Neural Network for Directed Graphs Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021) Authors Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, Matthew Hirn 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.
Zhang, Xitong; He, Yixuan; Brugnone, Nathan; Perlmutter, Michael; and Hirn, Matthew. (2020). "MagNet: A Neural Network for Directed Graphs". In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), 35th Conference on Neural Information Processing Systems (NeurIPS 2021). NeurIPS Proceedings.
PY - 2021
Y1 - 2021
N2 - 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 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 GNN architectures.
AB - 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 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 GNN architectures.
UR - https://proceedings.neurips.cc/paper_files/paper/2021/hash/e32084632d369461572832e6582aac36-Abstract.html
M3 - Chapter
BT - 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
ER -