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

Yunsheng Shi, Zhengjie Huang, shikun feng, Hui Zhong, Wenjin Wang, Yu Sun

Keywords: Unified Message Passing Model, Graph Neural Network, Label Propagation Algorithm, Semi-Supervised Classification.

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 \emph{feature propagation} by a neural network to make predictions, while LPA uses \emph{label propagation} across graph adjacency matrix to get results. However, there is still no good way to combine these two kinds of algorithms. In this paper, we proposed a new {\bf Uni}fied {\bf M}essage {\bf P}assaging Model (UniMP) that can incorporate \emph{feature propagation} and \emph{label propagation} with a shared message passing network, providing a better performance in semi-supervised classification. First, we adopt a Graph Transformer jointly label embedding to propagate both the feature and label information. Second, to train UniMP without overfitting in self-loop label information, we propose a masked label prediction strategy, in which some percentage of training labels are simply masked at random, and then predicted. UniMP conceptually unifies feature propagation and label propagation and be empirically powerful. It obtains new state-of-the-art semi-supervised classification results in Open Graph Benchmark (OGB).

One-sentence Summary: We propose a unified message passing model, incorporating feature propagation and label propagation for getting better performance in semi-supervised classification.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=9xtqt_dc1H