FCAD: Feature-coupled anisotropic diffusion for continuous graph learning

Author

Amitoz AZAD
Zhiyuan ZHANG, Singapore Management UniversityFollow

Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2025

Abstract

In this work, we propose a novel continuous graph neural network called FCAD (Feature-Coupled Anisotropic Diffusion) for the task of node classification on graphs. Our approach is motivated by the success of feature-coupled anisotropic diffusion PDEs in multivalued image restoration. Our method introduces a total variation regularization-inspired anisotropic term to control diffusion between nodes and incorporates a learnable parameterization for feature coupling during the diffusion process. Our model performs competitively against several GNN baselines for both heterophilous and homophilous graphs, demonstrating notable benefits for heterophilous graphs due to the learnable feature coupling.

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Areas of Excellence

Digital transformation

Publication

Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025), Bologna, Italy, October 25 -30

First Page

2546

Last Page

2553

ISBN

978164368-6318

Identifier

10.3233/FAIA251104

City or Country

Bologna, Italy

Citation

AZAD, Amitoz and ZHANG, Zhiyuan. FCAD: Feature-coupled anisotropic diffusion for continuous graph learning. (2025). Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025), Bologna, Italy, October 25 -30. 2546-2553.
Available at: https://ink.library.smu.edu.sg/sis_research/10691

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.

Additional URL

https://doi.org/10.3233/FAIA251104