Multi-scale graph contrastive learning for community detection in dynamic graphs

Abstract

Community detection in dynamic graphs is crucial for understanding the evolving relationships between entities in complex networks, such as social networks. These relationships change over time, driving the evolution of community structures. However, most existing research mainly focus on static graphs and cannot capture the evolution of community structures. Even when dynamic graphs are considered, they often rely on single-view graph information, leading to potential noise and suboptimal performance. To address these challenges, this paper proposes a new method called Multi-Scale Graph Contrastive Learning (MSGCL) for community detection in dynamic graphs. The MSGCL method first integrates the neighbor overlap similarity and topological structure similarity to enhance the graph features. Then, a multi-view graph representation learning module is proposed to learn local node representations and global graph representations of the graph, thereby addressing potential noise within single views. On this basis, a multi-scale contrastive learning module is proposed to improve the consistency and robustness of the node representations by leveraging both local-local and local-global contrastive learning. Finally, a Long Short-Term Memory (LSTM) module is incorporated to address the smooth transitions across time steps and achieve accurate community detection in dynamic graphs. Extensive experimental results demonstrate that MSGCL achieves superior performance across multiple datasets, with average improvements of 12.62% in NMI and 19.57% in ARI over the suboptimal method, outperforming the existing approaches. The code is available at https://anonymous.4open.science/r/MSGCL-340C/.