Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification

🤖 Plain-English Summary

Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful.

🔑 Key Findings

• GNN performs feature propagation by a neural network to make predictions, while LPA uses label propagation across graph adjacency matrix to get results.
• However, there is still no effective way to directly combine these two kinds of algorithms.
• To address this issue, we propose a novel Unified Message Passaging Model (UniMP) that can incorporate feature and label propagation at both training and inference time.

🔗 Related Resources