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.
- Pub Date:
- October 2021
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence;
- Statistics - Machine Learning
- 21 pages, 5 figures. Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) 2021