Discriminative Ordering Through Ensemble Consensus
This work addresses the challenge of comparing clustering models with varied cluster definitions and constraints, offering a more flexible evaluation metric for researchers and practitioners in data clustering.
The paper tackled the problem of evaluating clustering models with diverse definitions and constraints by proposing a discriminative ordering score based on ensemble consensus, which significantly outperformed other scoring methods in ranking models that best match the consensus.
Evaluating the performance of clustering models is a challenging task where the outcome depends on the definition of what constitutes a cluster. Due to this design, current existing metrics rarely handle multiple clustering models with diverse cluster definitions, nor do they comply with the integration of constraints when available. In this work, we take inspiration from consensus clustering and assume that a set of clustering models is able to uncover hidden structures in the data. We propose to construct a discriminative ordering through ensemble clustering based on the distance between the connectivity of a clustering model and the consensus matrix. We first validate the proposed method with synthetic scenarios, highlighting that the proposed score ranks the models that best match the consensus first. We then show that this simple ranking score significantly outperforms other scoring methods when comparing sets of different clustering algorithms that are not restricted to a fixed number of clusters and is compatible with clustering constraints.