Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning

TL;DR

Graph InfoClust (GIC) is a novel unsupervised graph representation learning method that leverages cluster-level information to produce richer, more informative node embeddings, improving performance on multiple graph analysis tasks.

Contribution

Introduces GIC, a method that incorporates cluster-level information via differentiable K-means and mutual information maximization, enhancing unsupervised graph embeddings.

Findings

GIC outperforms state-of-the-art methods in node classification, link prediction, and clustering.

Achieves 0.9% to 6.1% higher accuracy on average.

Effectively captures richer node and cluster interactions.

Abstract

Unsupervised (or self-supervised) graph representation learning is essential to facilitate various graph data mining tasks when external supervision is unavailable. The challenge is to encode the information about the graph structure and the attributes associated with the nodes and edges into a low dimensional space. Most existing unsupervised methods promote similar representations across nodes that are topologically close. Recently, it was shown that leveraging additional graph-level information, e.g., information that is shared among all nodes, encourages the representations to be mindful of the global properties of the graph, which greatly improves their quality. However, in most graphs, there is significantly more structure that can be captured, e.g., nodes tend to belong to (multiple) clusters that represent structurally similar nodes. Motivated by this observation, we propose a graph representation learning method called Graph InfoClust (GIC), that seeks to additionally capture cluster-level information content. These clusters are computed by a differentiable K-means method and are jointly optimized by maximizing the mutual information between nodes of the same clusters. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality. Experiments show that GIC outperforms state-of-art methods in various downstream tasks (node classification, link prediction, and node clustering) with a 0.9% to 6.1% gain over the best competing approach, on average.