Unifying Graph Convolutional Neural Networks and Label Propagation

Hongwei Wang, Jure Leskovec

Keywords: graph convolutional neural networks, label propagation, node classification

TL;DR: This paper studies theoretical relationships between Graph Convolutional Neural Networks (GCN) and Label Propagation Algorithm (LPA), then proposes an end-to-end model that unifies GCN and LPA for node classification.

Abstract: 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 are 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.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2002.06755/code)