Unifying Graph Convolutional Neural Networks and Label Propagation

17 Feb 2020  ·  Hongwei Wang, Jure Leskovec ·

Label Propagation (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptually similar, theoretical relation between LPA and GCN has not yet been investigated. Here we study the relationship between LPA and GCN in terms of two aspects: (1) feature/label smoothing where we analyze how the feature/label of one node is spread over its neighbors; And, (2) feature/label influence of how much the initial feature/label of one node influences the final feature/label of another node. Based on our theoretical analysis, we propose an end-to-end model that unifies GCN and LPA for node classification. In our unified model, edge weights are learnable, and the LPA serves as regularization to assist the GCN in learning proper edge weights that lead to improved classification performance. Our model can also be seen as learning attention weights based on node labels, which is more task-oriented than existing feature-based attention models. In a number of experiments on real-world graphs, our model shows superiority over state-of-the-art GCN-based methods in terms of node classification accuracy.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer GCN-LPA Accuracy 78.7 ± 0.6 # 10
Node Classification Coauthor CS GCN-LPA Accuracy 94.8 ± 0.4 # 6
Node Classification Coauthor Phy GCN-LPA Accuracy 96.9 ± 0.2 # 1
Node Classification Cora GCN-LPA Accuracy 88.5% ± 1.5% # 8
Node Classification Pubmed GCN-LPA Accuracy 87.8 ± 0.6 # 16