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 (25)
- Inductive Representation Learning on Large Graphs
- Deep Convolutional Networks on Graph-Structured Data
- Simplifying Graph Convolutional Networks
- Fourier Neural Operator for Parametric Partial Differential Equations
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Pitfalls of Graph Neural Network Evaluation
- Tune: A Research Platform for Distributed Model Selection and Training
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- A Generalization of Transformer Networks to Graphs
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- Network Geometry
- SIGN: Scalable Inception Graph Neural Networks
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks
- Differentiable Graph Module (DGM) for Graph Convolutional Networks
- Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noise
- Hamiltonian Graph Networks with ODE Integrators
- Lagrangian Neural Networks
- Graph Neural Ordinary Differential Equations
- Neural Embeddings of Graphs in Hyperbolic Space
- Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
- Learning Symbolic Physics with Graph Networks
- Continuous-in-Depth Neural Networks
- GRAND: Graph Neural Diffusion