DEEP CLUSTERING USING ADVERSARIAL NET BASED CLUSTERING LOSS

Kart-Leong Lim

Track: tiny / short paper (up to 4 pages)

Keywords: Deep clustering, adversarial net, KL divergence

Abstract:

Deep clustering is a recent deep learning technique which combines
deep learning with traditional unsupervised clustering. At the heart
of deep clustering is a loss function which penalizes samples for
being an outlier from their ground truth cluster centers in the latent
space. The probabilistic variant of deep clustering reformulates the
loss using KL divergence. Often, the main constraint of deep clustering
is the necessity of a closed form loss function to make backpropagation
tractable. Inspired by deep clustering and adversarial net, we reformulate
deep clustering as an adversarial net over traditional closed form
KL divergence. Training deep clustering becomes a task of minimizing
the encoder and maximizing the discriminator. At optimality, this
method theoretically approaches the JS divergence between the distribution
assumption of the encoder and the discriminator. We demonstrated the
performance of our proposed method on several well cited datasets
such as MNIST, REUTERS and CIFAR10, achieving on-par or better performance
with some of the state-of-the-art deep clustering methods.

Submission Number: 40