GRAND: Graph Neural Diffusion

By Benjamin Paul Chamberlain, James Rowbottom, Maria I. Gorinova, Stefan Webb, Emanuele Rossi, Michael M. Bronstein. International Conference on Machine Learning, 2021

391 citations recorded by the source corpus.

We present Graph Neural Diffusion (GRAND) that approaches deep learning on graphs as a continuous diffusion process and treats Graph Neural Networks (GNNs) as discretisations of an underlying PDE. In our model, the layer structure and topology correspond to the discretisation choices of temporal and spatial operators. Our approach allows a principled development of a broad new class of GNNs that are able to address the common plights of graph learning models such as depth, oversmoothing, and bottlenecks. Key to the success of our models are stability with respect to perturbations in the data and this is addressed for both implicit and explicit discretisation schemes. We develop linear and nonlinear versions of GRAND, which achieve competitive results on many standard graph benchmarks.

Subfields: Artificial Intelligence, Neurology

View Paper: https://www.semanticscholar.org/paper/95eee51c1cb1771e96cd182f47c90a7877461530

Citations in the corpus

• A Survey on Oversmoothing in Graph Neural Networks (2023, neutral): “More recent examples include Graph-Coupled Oscillator Networks (GraphCON) (Rusch et al., 2022), Graph Neural Diffusion (GRAND) (Chamberlain et al., 2021a), Beltrami Neural Diffusion (BLEND) (Chamberlain et al., 2021b), Neural Sheaf Diffusion (NSD) (Bodnar et al., 2022), and Gradient Glow Framework…”