Deep Divergence-Based Approach to Clustering

02/13/2019
by   Michael Kampffmeyer, et al.
36

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.

READ FULL TEXT

page 9

page 10

page 11

page 12

research
10/28/2022

Evaluating the Impact of Loss Function Variation in Deep Learning for Classification

The loss function is arguably among the most important hyperparameters f...
research
10/20/2019

Differentiable Deep Clustering with Cluster Size Constraints

Clustering is a fundamental unsupervised learning approach. Many cluster...
research
05/30/2023

Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach

The recent integration of deep learning and pairwise similarity annotati...
research
05/05/2019

Deep Discriminative Clustering Analysis

Traditional clustering methods often perform clustering with low-level i...
research
09/11/2019

Deep Prediction of Investor Interest: a Supervised Clustering Approach

We propose a novel deep learning architecture suitable for the predictio...
research
10/09/2018

Deep clustering: On the link between discriminative models and K-means

In the context of recent deep clustering studies, discriminative models ...
research
10/30/2018

Deep Learning for the Gaussian Wiretap Channel

End-to-end learning of communication systems with neural networks and pa...

Please sign up or login with your details

Forgot password? Click here to reset