Function Space Pooling For Graph Convolutional Networks

Convolutional layers in graph neural networks are a fundamental type of layer which output a representation or embedding of each graph vertex. The representation typically encodes information about the vertex in question and its neighbourhood. If one wishes to perform a graph centric task such as graph classification the set of vertex representations must be integrated or pooled to form a graph representation. We propose a novel pooling method which transforms a set of vertex representations into a function space representation. Experiential results demonstrate that the proposed method outperforms standard pooling methods of computing the sum and mean vertex representation.