Simplifying Clustering with Graph Neural Networks
This work simplifies clustering for graph data, but it is incremental as it builds on existing spectral clustering and GNN methods.
The paper tackled the problem of spectral clustering by showing that a graph neural network with appropriate message passing layers can produce good cluster assignments using only a balancing term, eliminating the need for a local quadratic variation term, and demonstrated effectiveness in clustering performance and computation time on attributed graph datasets.
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.