Beyond One Solution: The Case for a Comprehensive Exploration of Solution Space in Community Detection

Abstract

This article explores the importance of examining the solution space in community detection, highlighting its role in achieving reliable results when dealing with real-world problems. A Bayesian framework is used to estimate the stability of the solution space and classify it into categories Single, Dominant, Multiple, Sparse or Empty. By applying this approach to real-world networks, the study highlights the importance of considering multiple solutions rather than relying on a single partition. This ensures more reliable results and efficient use of computational resources in community detection analysis.

References in corpus (19)

• Fast unfolding of communities in large networks
• Finding and evaluating community structure in networks
• From Louvain to Leiden: guaranteeing well-connected communities
• Uncovering the overlapping community structure of complex networks in nature and society
• The structure of scientific collaboration networks
• Near linear time algorithm to detect community structures in large-scale networks
• Comparing community structure identification
• Hierarchical structure and the prediction of missing links in networks
• Community detection in networks: A user guide
• The performance of modularity maximization in practical contexts
• An information-theoretic framework for resolving community structure in complex networks
• A Review of Stochastic Block Models and Extensions for Graph Clustering
• 20 years of network community detection
• Exploring the solution landscape enables more reliable network community detection
• Fast consensus clustering in complex networks
• Embedding-based Silhouette Community Detection
• Network communities within and across borders
• Mapping robust multiscale communities in chromosome contact networks
• Enhancing Stability and Assessing Uncertainty in Community Detection through a Consensus-based Approach