CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning

TL;DR

CAGNN introduces a cluster-aware GNN that refines graph topology based on clustering to improve unsupervised node embedding quality, achieving significant accuracy gains in real-world benchmarks.

Contribution

The paper proposes a novel cluster-aware GNN model that refines graph structure using clustering, enhancing unsupervised node embedding learning without labeled data.

Findings

Over 7% accuracy improvement in node clustering

Effective refinement of graph topology based on cluster labels

Superior performance over baseline methods in benchmarks

Abstract

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large number of labeled nodes, which may not be accessible in real-world graph data. In this paper, we present a novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques. In CAGNN, we perform clustering on the node embeddings and update the model parameters by predicting the cluster assignments. Moreover, we observe that graphs often contain inter-class edges, which mislead the GNN model to aggregate noisy information from neighborhood nodes. We further refine the graph topology by strengthening intra-class edges and reducing node connections between different classes based on cluster labels, which better preserves cluster structures in the embedding space. We conduct comprehensive experiments on two benchmark tasks using real-world datasets. The results demonstrate the superior performance of the proposed model over existing baseline methods. Notably, our model gains over 7% improvements in terms of accuracy on node clustering over state-of-the-arts.