Amortized Probabilistic Detection of Communities in Graphs
This work addresses a limitation in graph neural network-based community detection for scientific applications by enabling variable cluster numbers and probabilistic handling, though it is incremental as it builds on existing amortized clustering methods.
The authors tackled the problem of community detection in graphs by proposing an amortized probabilistic framework that combines graph neural networks with amortized clustering, which eliminates the need to pre-specify the number of communities and provides uncertainty quantification. They demonstrated improved performance on synthetic and real datasets compared to previous methods.
Learning community structures in graphs has broad applications across scientific domains. While graph neural networks (GNNs) have been successful in encoding graph structures, existing GNN-based methods for community detection are limited by requiring knowledge of the number of communities in advance, in addition to lacking a proper probabilistic formulation to handle uncertainty. We propose a simple framework for amortized community detection, which addresses both of these issues by combining the expressive power of GNNs with recent methods for amortized clustering. Our models consist of a graph representation backbone that extracts structural information and an amortized clustering network that naturally handles variable numbers of clusters. Both components combine into well-defined models of the posterior distribution of graph communities and are jointly optimized given labeled graphs. At inference time, the models yield parallel samples from the posterior of community labels, quantifying uncertainty in a principled way. We evaluate several models from our framework on synthetic and real datasets, and demonstrate improved performance compared to previous methods. As a separate contribution, we extend recent amortized probabilistic clustering architectures by adding attention modules, which yield further improvements on community detection tasks.