A Distributional Approach for Soft Clustering Comparison and Evaluation
This work addresses the need for better evaluation criteria in soft clustering, which is important for researchers and practitioners in data mining and machine learning, though it appears incremental as it builds on existing hard clustering measures.
The paper tackles the problem of evaluating soft clustering algorithms by proposing a general method based on interpreting soft clustering as distributions over hard clusterings, which addresses limitations in existing comparison measures and accounts for uncertainty, with results demonstrated through an illustrative experiment.
The development of external evaluation criteria for soft clustering (SC) has received limited attention: existing methods do not provide a general approach to extend comparison measures to SC, and are unable to account for the uncertainty represented in the results of SC algorithms. In this article, we propose a general method to address these limitations, grounding on a novel interpretation of SC as distributions over hard clusterings, which we call \emph{distributional measures}. We provide an in-depth study of complexity- and metric-theoretic properties of the proposed approach, and we describe approximation techniques that can make the calculations tractable. Finally, we illustrate our approach through a simple but illustrative experiment.