NeurIPS 2021poster95 citations

Beltrami Flow and Neural Diffusion on Graphs

Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni, Xiaowen Dong, Michael M. Bronstein

Abstract

We propose a novel class of graph neural networks based on the discretized 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, topology evolution. The resulting model generalizes many popular graph neural networks and achieves state-of-the-art results on several benchmarks.

Geometric Deep LearningGraph Neural NetworkDiffusion
BibTeX
@inproceedings{
chamberlain2021beltrami,
title={Beltrami Flow and Neural Diffusion on Graphs},
author={Benjamin Paul Chamberlain and James Rowbottom and Davide Eynard and Francesco Di Giovanni and Xiaowen Dong and Michael M. Bronstein},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=4YlE2huxEsl}
}
Beltrami Flow and Neural Diffusion on Graphs · NeurIPS 2021