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

TL;DR

This paper introduces UniMP, a unified message passing model that combines feature and label propagation using a Graph Transformer, achieving state-of-the-art results in semi-supervised graph classification.

Contribution

The paper proposes UniMP, a novel model that unifies feature and label propagation with a masked label prediction strategy, enhancing semi-supervised classification performance.

Findings

Achieves state-of-the-art results on OGB benchmark.

Effectively combines feature and label propagation.

Introduces masked label prediction to prevent overfitting.

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).