Diffusion Improves Graph Learning

Understand

Graph convolution is the core of most Graph Neural Networks (GNNs) and usually approximated by message passing between direct (one-hop) neighbors.

• In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC).
• GDC leverages generalized graph diffusion, examples of which are the heat kernel and personalized PageRank.
• It alleviates the problem of noisy and often arbitrarily defined edges in real graphs.