Beltrami Flow and Neural Diffusion on Graphs
arXiv:2110.09443
Abstract
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positional encodings derived from the graph topology and jointly evolved by the Beltrami flow, producing simultaneously continuous feature learning and topology evolution. The resulting model generalises many popular graph neural networks and achieves state-of-the-art results on several benchmarks.
21 pages, 5 figures. Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) 2021
References in corpus (9)
- Deep Convolutional Networks on Graph-Structured Data
- Simplifying Graph Convolutional Networks
- A Generalization of Transformer Networks to Graphs
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
- Hamiltonian Graph Networks with ODE Integrators
- Learning Symbolic Physics with Graph Networks
- Continuous-in-Depth Neural Networks
- GRAND: Graph Neural Diffusion