Clique pooling for graph classification
This work addresses graph classification for machine learning researchers, offering an interpretable and topology-based pooling method, but it is incremental as it builds on existing graph neural network frameworks.
The authors tackled graph classification by proposing a novel graph pooling operation based on cliques, which is purely topological and nonparametric, and demonstrated competitive performance on standard benchmarks when integrated into GCN and GraphSAGE architectures, as well as in CNNs.
We propose a novel graph pooling operation using cliques as the unit pool. As this approach is purely topological, rather than featural, it is more readily interpretable, a better analogue to image coarsening than filtering or pruning techniques, and entirely nonparametric. The operation is implemented within graph convolution network (GCN) and GraphSAGE architectures and tested against standard graph classification benchmarks. In addition, we explore the backwards compatibility of the pooling to regular graphs, demonstrating competitive performance when replacing two-by-two pooling in standard convolutional neural networks (CNNs) with our mechanism.