Deep Divergence-Based Approach to Clustering

Abstract

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.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Striving for Simplicity: The All Convolutional Net
• Proceedings of the 29th International Conference on Machine Learning (ICML-12)
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• DRAW: A Recurrent Neural Network For Image Generation
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
• Mini-Batch Spectral Clustering

Cited by in corpus (6)

• A Unifying Review of Deep and Shallow Anomaly Detection
• A Clustering-guided Contrastive Fusion for Multi-view Representation Learning
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• Simplifying Clustering with Graph Neural Networks
• Leveraging tensor kernels to reduce objective function mismatch in deep clustering
• Deep Bregman Divergence for Contrastive Learning of Visual Representations