A GraphSAGE-Enhanced Label Diffusion Approach for Scalable Community Detection in Large Networks

Abstract: Community detection in complex networks remains a fundamental problem in network science, with wide-ranging applications from sociology to biology and recommendation systems. Building on recent advances in label diffusion techniques, we propose a novel hybrid approach—GraphSAGE-LBLD—that combines the structural awareness of the GraphSAGE embedding model with the local balance and speed advantages of the Label Balanced Label Diffusion (LBLD) algorithm. Our method integrates representation learning into the label propagation process, allowing for more semantically meaningful diffusion and improved stability across diverse network topologies. We empirically evaluate GraphSAGE-LBLD on multiple real-world SNAP datasets and benchmark against Louvain, classic Label Propagation, and the original LBLD. Results demonstrate that our model consistently achieves higher modularity and Normalized Mutual Information (NMI) scores, while maintaining comparable runtime. The integration of GraphSAGE enhances the representation of local neighbourhoods, resulting in finer community boundaries and better detection of small or overlapping clusters. Our method offers a practical, scalable, and more accurate alternative for modern community detection tasks.

Keywords: Community Detection, GraphSAGE, Label Propagation, Graph Neural Networks, Node Embeddings, K-core, Graph Autoencoder, Modularity, Weighted Diffusion, Cosine Similarity.