Mingliang Hou

Spectral analysis of graph neighborhoods reveals a surprisingly effective and efficient way to boost anomaly detection, consistently outperforming existing GNN-based methods.

Multi-view learning with prototype-based correction significantly boosts the robustness of thyroid nodule ultrasound classification across different ultrasound devices and clinical environments.

Graph condensation, while shrinking massive datasets for GNN training, can inadvertently amplify biases – until now.