A Multi-Strategy Approach to Overcoming Bias in Community Detection Evaluation
This work addresses the issue of biased results in community detection evaluation for researchers and practitioners, offering an incremental improvement by integrating multiple existing strategies.
The paper tackles the problem of biased evaluation in community detection by proposing a multi-strategy approach that uses consensus among strategies and comparisons with ground truths to provide robust quality assessments, with experiments on real and synthetic networks demonstrating its effectiveness.
Community detection is key to understand the structure of complex networks. However, the lack of appropriate evaluation strategies for this specific task may produce biased and incorrect results that might invalidate further analyses or applications based on such networks. In this context, the main contribution of this paper is an approach that supports a robust quality evaluation when detecting communities in real-world networks. In our approach, we use multiple strategies that capture distinct aspects of the communities. The conclusion on the quality of these communities is based on the consensus among the strategies adopted for the structural evaluation, as well as on the comparison with communities detected by different methods and with their existing ground truths. In this way, our approach allows one to overcome biases in network data, detection algorithms and evaluation metrics, thus providing more consistent conclusions about the quality of the detected communities. Experiments conducted with several real and synthetic networks provided results that show the effectiveness of our approach.