Graph Neural Network

Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification against Label Noise
Graph neural networks (GNNs) based on message passing have achieved remarkable performance in graph machine learning. By combining it …
Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models
The open-world test dataset is often mixed with out-of-distribution (OOD) samples, where the deployed models will struggle to make …
The Heterophily Snowflake Hypothesis: Training and Empowering GNN for Heterophilic Graphs
Graph Neural Networks (GNNs) have become pivotal tools for a range of graph-based learning tasks. Notably, most current GNN …