Unifying Graph Convolutional Neural Networks and Label Propagation

TL;DR

This paper explores the theoretical relationship between Label Propagation and Graph Convolutional Networks, proposing a unified model that improves node classification by learning task-oriented edge weights.

Contribution

It introduces a novel end-to-end model unifying LPA and GCN, with learnable edge weights and label-based attention, enhancing classification accuracy.

Findings

Unified model outperforms state-of-the-art GCN methods

Learnable edge weights improve node classification

LPA acts as regularization in the unified framework

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 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.