Continual Learning in Generative Adversarial Nets
This work addresses the challenge of sequential data modeling for AI systems that need to handle evolving datasets, though it is incremental as it applies known methods to GANs.
The paper tackles the problem of catastrophic forgetting in generative adversarial networks (GANs) when trained on sequential data distributions, adapting existing techniques to enable continual learning and generative modeling across distinct distributions.
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.