Maximal Independent Sets for Pooling in Graph Neural Networks
This addresses a key bottleneck in graph neural networks for researchers and practitioners, though it appears incremental as it builds on existing pooling concepts.
The paper tackles the lack of pooling methods for graphs that maintain connectivity and allow full consideration of nodes, by proposing three pooling methods based on maximal independent sets to avoid issues like disconnection or low decimation. Experimental results show the relevance of these constraints for graph pooling.
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.