Machine learning informed by micro- and mesoscopic statistical physics methods for community detection

Community detection plays a crucial role in understanding the structural organization of complex networks. Previous methods, particularly those from statistical physics, primarily focus on the analysis of mesoscopic network structures and often struggle to integrate fine-grained node similarities. To address this limitation, we propose a low-complexity framework that integrates machine learning to embed micro-level node-pair similarities into mesoscopic community structures. By leveraging ensemble learning models, our approach enhances both structural coherence and detection accuracy. Experimental evaluations on artificial and real-world networks demonstrate that our framework consistently outperforms conventional methods, as well as state-of-the-art embedding-based and learning-based approaches, achieving higher modularity and improved accuracy in normalized mutual information and adjusted rand index. Notably, even in the complete absence of ground-truth community information, our approach still achieves substantial improvements in algorithmic accuracy based on the principles of statistical-physics methods. When ground-truth labels are available, it yields the most accurate detection results, effectively recovering real-world community structures while minimizing misclassifications. To further explain the performance of our framework, we analyze the correlation between node-pair similarity and evaluation metrics. The results reveal a strong and statistically significant correlation, underscoring the critical role of node-pair similarity in enhancing detection accuracy. Overall, our findings highlight the synergy between machine learning and statistical physics, demonstrating how machine learning techniques can enhance network analysis and uncover complex structural patterns.