On the robustness of graph neural diffusion to topology perturbations

• Main Authors: Song, Yang, Kang, Qiyu, Wang, Sijie, Zhao, Kai, Tay, Wee Peng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Graph Neural Networks; Deep Learning
• Online Access: https://hdl.handle.net/10356/166693; https://proceedings.neurips.cc/; https://nips.cc/Conferences/2022
• Institution: Nanyang Technological University

Neural diffusion on graphs is a novel class of graph neural networks that has attracted increasing attention recently. The capability of graph neural partial differential equations (PDEs) in addressing common hurdles of graph neural networks (GNNs), such as the problems of over-smoothing and bottlen...