Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
This addresses a bottleneck in graph-based semi-supervised learning for researchers and practitioners, though it is incremental as it builds on existing message passing methods.
The paper tackles the problem of combining graph neural networks and label propagation algorithms for semi-supervised classification by proposing UniMP, which integrates feature and label propagation using a Graph Transformer and masked label prediction, achieving new state-of-the-art results on the Open Graph Benchmark.
Graph neural network (GNN) and label propagation algorithm (LPA) are both message passing algorithms, which have achieved superior performance in semi-supervised classification. 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. First, UniMP adopts a Graph Transformer network, taking feature embedding and label embedding as input information for propagation. Second, to train the network without overfitting in self-loop input label information, UniMP introduces a masked label prediction strategy, in which some percentage of input label information are masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and is empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).