Simplifying Clustering with Graph Neural Networks

TL;DR

This paper introduces a graph neural network approach that simplifies spectral clustering by focusing on a single balancing term, leading to efficient and effective clustering results on attributed graph datasets.

Contribution

It demonstrates that GNNs can generate high-quality cluster assignments by optimizing only the balancing term, simplifying the spectral clustering process.

Findings

Effective clustering performance on attributed graph datasets

Reduced computation time compared to traditional spectral clustering

GNN-based approach simplifies the clustering process

Abstract

The objective functions used in spectral clustering are usually composed of two terms: i) a term that minimizes the local quadratic variation of the cluster assignments on the graph and; ii) a term that balances the clustering partition and helps avoiding degenerate solutions. This paper shows that a graph neural network, equipped with suitable message passing layers, can generate good cluster assignments by optimizing only a balancing term. Results on attributed graph datasets show the effectiveness of the proposed approach in terms of clustering performance and computation time.