Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MagNet: A Neural Network for Directed Graphs

About

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.

Xitong Zhang, Yixuan He, Nathan Brugnone, Michael Perlmutter, Matthew Hirn• 2021

Related benchmarks

TaskDatasetResultRank
Node ClassificationCiteseer (test)
Accuracy0.7714
729
Node ClassificationCora (test)
Mean Accuracy82.63
687
Node ClassificationChameleon
Accuracy58.22
549
Node ClassificationSquirrel
Accuracy39.01
500
Node Classificationogbn-arxiv (test)
Accuracy68.5
382
Node ClassificationCiteseer
Accuracy66.5
275
Node ClassificationSquirrel (test)
Mean Accuracy42.7
234
Node ClassificationChameleon (test)
Mean Accuracy58.22
230
Node ClassificationTexas (test)
Mean Accuracy83.3
228
Node ClassificationCora-ML
Accuracy79.7
228
Showing 10 of 31 rows

Other info

Follow for update