Unifying Graph Convolutional Neural Networks and Label Propagation

Hongwei Wang, Jure Leskovec

Keywords: graph convolutional neural networks, label propagation, semi-supervised 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, it is unclear how LPA and GCN can be combined under a unified framework to improve node classification. Here we study the relationship between LPA and GCN in terms of feature/label influence, in which we characterize how much the initial feature/label of one node influences the final feature/label of another node in GCN/LPA. Based on our theoretical analysis, we propose an end-to-end model that combines GCN and LPA. 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 the weights for edges based on node labels, which is more task-oriented than existing feature-based attention models and topology-based diffusion models. In a number of experiments on real-world graphs, our model shows superiority over state-of-the-art graph neural networks in terms of node classification accuracy.

One-sentence Summary: 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 semi-supervised node 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

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

Reviewed Version (pdf): https://openreview.net/references/pdf?id=WeyE1GLnfq