Feature Transportation Improves Graph Neural Networks

Authors

  • Moshe Eliasof University of Cambridge Ben-Gurion University of the Negev
  • Eldad Haber University of British Columbia
  • Eran Treister Ben-Gurion University of the Negev

DOI:

https://doi.org/10.1609/aaai.v38i11.29073

Keywords:

ML: Graph-based Machine Learning

Abstract

Graph neural networks (GNNs) have shown remarkable success in learning representations for graph-structured data. However, GNNs still face challenges in modeling complex phenomena that involve feature transportation. In this paper, we propose a novel GNN architecture inspired by Advection-Diffusion-Reaction systems, called ADR-GNN. Advection models feature transportation, while diffusion captures the local smoothing of features, and reaction represents the non-linear transformation between feature channels. We provide an analysis of the qualitative behavior of ADR-GNN, that shows the benefit of combining advection, diffusion, and reaction. To demonstrate its efficacy, we evaluate ADR-GNN on real-world node classification and spatio-temporal datasets, and show that it improves or offers competitive performance compared to state-of-the-art networks.

Published

2024-03-24

How to Cite

Eliasof, M., Haber, E., & Treister, E. (2024). Feature Transportation Improves Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 38(11), 11874-11882. https://doi.org/10.1609/aaai.v38i11.29073

Issue

Section

AAAI Technical Track on Machine Learning II