Feature Transportation Improves Graph Neural Networks
Moshe Eliasof, Eldad Haber, Eran Treister
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.
BibTeX
@article{Eliasof_Haber_Treister_2024, title={Feature Transportation Improves Graph Neural Networks}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29073}, DOI={10.1609/aaai.v38i11.29073}, abstractNote={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.}, number={11}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Eliasof, Moshe and Haber, Eldad and Treister, Eran}, year={2024}, month={Mar.}, pages={11874-11882} }