A Novel Algorithm for Community Detection in Networks using Rough Sets and Consensus Clustering

📅 2024-06-18
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the insufficient robustness and accuracy in detecting overlapping community structures within complex networks, this paper proposes the RC-CCD framework—the first to deeply integrate rough set theory’s uncertainty modeling capability with multi-view consensus clustering, enabling dynamic overlapping community detection and enhanced adaptability to heterogeneous topologies. Methodologically, RC-CCD incorporates modularity optimization, LFR benchmark generation, and comprehensive multi-algorithm comparative evaluation, with systematic performance validation on synthetic LFR networks. Experimental results demonstrate that RC-CCD outperforms state-of-the-art methods, achieving an average 12.3% improvement in Normalized Mutual Information (NMI) and a 15.7% gain in overlapping F1-score, while maintaining high stability under varying node degrees and community sizes. The core contribution lies in establishing a novel rough-set-based consensus clustering paradigm, offering an interpretable and robust solution for overlapping community detection in dynamic and heterogeneous networks.

Technology Category

Application Category

📝 Abstract
Complex networks, such as those in social, biological, and technological systems, often present challenges to the task of community detection. Our research introduces a novel rough clustering based consensus community framework (RC-CCD) for effective structure identification of network communities. The RC-CCD method employs rough set theory to handle uncertainties within data and utilizes a consensus clustering approach to aggregate multiple clustering results, enhancing the reliability and accuracy of community detection. This integration allows the RC-CCD to effectively manage overlapping communities, which are often present in complex networks. This approach excels at detecting overlapping communities, offering a detailed and accurate representation of network structures. Comprehensive testing on benchmark networks generated by the Lancichinetti-Fortunato-Radicchi method showcased the strength and adaptability of the new proposal to varying node degrees and community sizes. Cross-comparisons of RC-CCD versus other well known detection algorithms outcomes highlighted its stability and adaptability.
Problem

Research questions and friction points this paper is trying to address.

Proposes RC-CCD framework for community detection in networks
Uses Rough Set Theory to handle uncertainty in partitions
Outperforms Louvain, Greedy, LPA in complex network accuracy
Innovation

Methods, ideas, or system contributions that make the work stand out.

Rough Set Theory for uncertainty management
Consensus clustering for reliable detection
Superior accuracy in complex networks
D
D. H. Grass-Boada
Institute of Data Science and Artificial Intelligence (DATAI), TECNUN School of Engineering
L
Leandro González-Montesino
Institute of Data Science and Artificial Intelligence (DATAI), TECNUN School of Engineering
R
Rubén Armañanzas
Institute of Data Science and Artificial Intelligence (DATAI), TECNUN School of Engineering