Reduced network extremal ensemble learning (RenEEL) scheme for community detection in complex networks.

Area of Science:

• Network Science
• Machine Learning
• Data Mining

Background:

• Community detection is crucial for understanding complex network structures.
• Existing methods face challenges in accuracy and efficiency for large networks.

Purpose of the Study:

• Introduce a novel ensemble learning scheme for enhanced community detection.
• Improve the accuracy of identifying node partitions that maximize modularity.

Main Methods:

• Developed Extremal Ensemble Learning (EEL), an iterative machine learning algorithm.
• Utilized iterative extremal updating of network partitions to refine community structures.
• Employed a reduced network approach for computational efficiency.

Main Results:

• EEL successfully identified optimal node partitions maximizing modularity.
• The scheme demonstrated superior performance on benchmark network datasets.
• Outperformed all known methods in finding the maximum modularity partition.

Conclusions:

• Extremal Ensemble Learning offers a highly effective and efficient solution for community detection.
• The method advances the field of network analysis and machine learning applications.