TY - CHAP
T1 - MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian
AU - He, Yixuan
AU - Perlmutter, Michael
AU - Reinert, Gesine
AU - Cucuringu, Mihai
N1 - Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks (GNNs) for such networks. Here we int...
He, Yixuan; Perlmutter, Michael; Reinert, Gesine; and Cucuringu, Mihai. (2022). "MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian". In B. Rieck and R. Pascanu (Eds.), Proceedings of the First Learning on Graphs Conference (LoG 2022) (Proceedings of Machine Learning Research series, Volume 198, pp. 6:1 - 6:25). Proceedings of Machine Learning Research.
PY - 2022
Y1 - 2022
N2 - Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks (GNNs) for such networks. Here we introduce a signed directed Laplacian matrix, which we call the magnetic signed Laplacian, as a natural generalization of both the signed Laplacian on signed graphs and the magnetic Laplacian on directed graphs. We then use this matrix to construct a novel efficient spectral GNN architecture and conduct extensive experiments on both node clustering and link prediction tasks. In these experiments, we consider tasks related to signed information, tasks related to directional information, and tasks related to both signed and directional information. We demonstrate that our proposed spectral GNN is effective for incorporating both signed and directional information, and attains leading performance on a wide range of data sets. Additionally, we provide a novel synthetic network model, which we refer to as the Signed Directed Stochastic Block Model, and a number of novel real-world data sets based on lead-lag relationships in financial time series.
AB - Signed and directed networks are ubiquitous in real-world applications. However, there has been relatively little work proposing spectral graph neural networks (GNNs) for such networks. Here we introduce a signed directed Laplacian matrix, which we call the magnetic signed Laplacian, as a natural generalization of both the signed Laplacian on signed graphs and the magnetic Laplacian on directed graphs. We then use this matrix to construct a novel efficient spectral GNN architecture and conduct extensive experiments on both node clustering and link prediction tasks. In these experiments, we consider tasks related to signed information, tasks related to directional information, and tasks related to both signed and directional information. We demonstrate that our proposed spectral GNN is effective for incorporating both signed and directional information, and attains leading performance on a wide range of data sets. Additionally, we provide a novel synthetic network model, which we refer to as the Signed Directed Stochastic Block Model, and a number of novel real-world data sets based on lead-lag relationships in financial time series.
UR - https://proceedings.mlr.press/v198/he22c.html
M3 - Chapter
BT - Proceedings of the First Learning on Graphs Conference
ER -