Deep Conditional Gaussian Mixture Model for Constrained Clustering

TL;DR

This paper introduces DC-GMM, a deep generative model for constrained clustering that effectively incorporates prior domain knowledge through probabilistic constraints, leading to improved clustering accuracy and robustness.

Contribution

The paper presents a novel deep probabilistic framework, DC-GMM, that explicitly integrates pairwise constraints into the clustering process using variational inference.

Findings

DC-GMM outperforms existing methods on multiple datasets.

The model demonstrates robustness to noisy constraints.

Effective in real-world applications with partial labels.

Abstract

Constrained clustering has gained significant attention in the field of machine learning as it can leverage prior information on a growing amount of only partially labeled data. Following recent advances in deep generative models, we propose a novel framework for constrained clustering that is intuitive, interpretable, and can be trained efficiently in the framework of stochastic gradient variational inference. By explicitly integrating domain knowledge in the form of probabilistic relations, our proposed model (DC-GMM) uncovers the underlying distribution of data conditioned on prior clustering preferences, expressed as pairwise constraints. These constraints guide the clustering process towards a desirable partition of the data by indicating which samples should or should not belong to the same cluster. We provide extensive experiments to demonstrate that DC-GMM shows superior clustering performances and robustness compared to state-of-the-art deep constrained clustering methods on a wide range of data sets. We further demonstrate the usefulness of our approach on two challenging real-world applications.