Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling

arXiv:1910.11436v3 Announce Type: replace
Abstract: In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed …

abstract arxiv building compute cs.lg fundamental global gnns graph graph neural networks graphs hierarchical learn math.sp ndp networks neural networks node operators pooling representation representation learning stat.ml type work