Agrupamento profundo de grafos usando redes neurais de grafos e seleção de sementes

Abstract

Clustering plays a fundamental role in attributed graphs, which incorporate both topological structure and node attributes represented as feature vectors. Deep clustering methods based on Graph Neural Networks (GNNs) have proven effective in extracting patterns from such data. Most existing approaches use a traditional clustering algorithm to identify representative elements, which are later employed in the training of the GNN and the clustering task. However, when selecting representative elements, these clustering algorithms consider only the feature vector of each instance, neglecting topological information. This limitation negatively impacts the GNN learning process. To address this issue, we propose Deep Graph Clustering via Graph Neural Network and Seed Selection (DGCSS), a model consisting of three modules: (1) the seed selection module, which iden- tifies representative nodes; (2) the embedding module, which employs a graph attentional network to capture global topological information; and (3) the self-supervised module, which leverages the representative nodes to guide the clustering task. An advantage of our algorithm is that it integrates both the topological structure and node attributes across all modules to identify representative elements. This is the first GNN-based clustering algorithm that incorporates seed selection, establishing a significant reference for future research. The empirical analysis of real world graphs provides evidence that the use of seeds is competitive when compared to traditional algorithms, such as K-Means combined with GNNs.