2023
USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network
AAAI 2023technical
Unsupervised/self-supervised graph neural networks (GNN) are susceptible to the inherent randomness in the input graph data, which adversely affects the model's performance in downstream tasks. In this paper, we propose USER, an unsupervised and robust version of GNN based on structural entropy, to…