Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjin Wang, Yu Sun
TL;DR
Semi-supervised node classification benefits from both feature propagation and label propagation, but prior methods did not unify these within a single end-to-end message-passing model. UniMP uses a Graph Transformer to jointly propagate node features and label embeddings and employs a masked label prediction strategy to avoid leakage during training. The approach yields state-of-the-art results on Open Graph Benchmark datasets ogbn-products, ogbn-proteins, and ogbn-arxiv, with extensive ablations validating the benefits of unifying propagation and masking. This work demonstrates that integrating label propagation into GNNs is a practical, scalable path to improving graph-based semi-supervised learning.
Abstract
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).