Deep Divergence-Based Approach to Clustering
This work addresses the challenge of unsupervised deep clustering, an incremental advancement in a nascent field.
The paper tackles the problem of designing loss functions for deep clustering by introducing a network that uses information-theoretic divergence measures with geometric regularization to avoid degenerate partitions, achieving competitive performance on benchmarks and real datasets without pre-training.
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning, this line of research is in its infancy, and how to design and optimize suitable loss functions to train deep neural networks for clustering is still an open question. Our contribution to this emerging field is a new deep clustering network that leverages the discriminative power of information-theoretic divergence measures, which have been shown to be effective in traditional clustering. We propose a novel loss function that incorporates geometric regularization constraints, thus avoiding degenerate structures of the resulting clustering partition. Experiments on synthetic benchmarks and real datasets show that the proposed network achieves competitive performance with respect to other state-of-the-art methods, scales well to large datasets, and does not require pre-training steps.