Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

Understand

Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data.

• Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification.
• In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size.
• Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes.