Continual Learning in Generative Adversarial Nets

TL;DR

This paper addresses the challenge of continual learning in generative adversarial networks, proposing methods to prevent catastrophic forgetting when modeling sequentially observed distributions.

Contribution

It adapts recent continual learning techniques to GANs, enabling them to learn multiple distributions sequentially without forgetting previous ones.

Findings

Successfully prevents catastrophic forgetting in GANs during sequential training

Enables GANs to model multiple distributions over time

Improves stability of generative models in continual learning scenarios

Abstract

Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequentially, such as when different classes are encountered over time. Although conditional variations of deep generative models permit multiple distributions to be modeled by a single network in a disentangled fashion, they are susceptible to catastrophic forgetting when the distributions are encountered sequentially. In this paper, we adapt recent work in reducing catastrophic forgetting to the task of training generative adversarial networks on a sequence of distinct distributions, enabling continual generative modeling.