3 papers
cs.LG2025
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space
Xin He, Yili Wang, Wenqi Fan +4
Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of over-smoothing as the model depth increases, which…
cs.LG2025
Graph Defense Diffusion Model
Xin He, Wenqi Fan, Yili Wang +4
Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this…
cs.IR2024
Automatic Self-supervised Learning for Social Recommendations
Xin He, Wenqi Fan, Mingchen Sun +2
In recent years, researchers have leveraged social relations to enhance recommendation performance. However, most existing social recommendation methods require carefully designed…