Simplifying Clustering with Graph Neural Networks

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.

References in corpus (9)

• DeepWalk: Online Learning of Social Representations
• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Understanding Pooling in Graph Neural Networks
• Deep Divergence-Based Approach to Clustering
• Spectral Clustering with Graph Neural Networks for Graph Pooling
• A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions