Adaptive propagation graph convolutional network

Graph convolutional networks (GCNs) are a family ofneural network models that perform inference on graph data byinterleaving vertexwise operations and message-passing exchanges acrossnodes. Concerning the latter, two key questions arise: 1) how to design adifferentiable exchange protocol (e.g., a one-hop Laplacian smoothing inthe original GCN) and 2) how to characterize the tradeoff in complexitywith respect to the local updates. In this brief, we show that the state-of-the-art results can be achieved by adapting the number of communicationsteps independently at every node. In particular, we endow each node witha halting unit (inspired by Graves’ adaptive computation time [1]) thatafter every exchange decides whether to continue communicating or not.We show that the proposed adaptive propagation GCN (AP-GCN)achieves superior or similar results to the best proposed models so faron a number of benchmarks while requiring a small overhead in termsof additional parameters. We also investigate a regularization term toenforce an explicit tradeoff between communication and accuracy. Thecode for the AP-GCN experiments is released as an open-source library.