Graph Neural Networks for Signed and Directed Graphs

With an increasing number of applications where data can be represented as graphs, graph neural networks (GNNs) are a useful tool to apply deep learning to graph data. Signed networks, with both positive and negative edge weights, and directed networks, with asymmetric sending and receiving patterns, are important types of networks that are linked to many real-world problems. In this talk, I will introduce two graph neural network models for node clustering in signed networks and directed networks, respectively, as well as a spectral graph neural network model based on a novel notion of magnetic signed Laplacian for signed directed graphs. I will also share with you a PyTorch library for signed and directed GNNs.

Bio
sherylhyx.github.io