Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods

Abstract

Generative adversarial networks (GANs) suffer from catastrophic forgetting when learning multiple consecutive tasks. Parameter regularization methods that constrain the parameters of the new model in order to be close to the previous model through parameter importance are effective in overcoming forgetting. Many parameter regularization methods have been tried, but each of them is only suitable for limited types of neural networks. Aimed at GANs, this paper proposes a unified framework called Memory Protection GAN (MPGAN), in which many parametrization methods can be used to overcome forgetting. The proposed framework includes two modules: Protecting Weights in Generator and Controller. In order to incorporate parameter regularization methods into MPGAN, the Protecting Weights in Generator module encapsulates different parameter regularization methods into a "container", and consolidates the most important parameters in the generator through a parameter regularization method selected from the container. In order to differentiate tasks, the Controller module creates unique tags for the tasks. Another problem with existing parameter regularization methods is their low accuracy in measuring parameter importance. These methods always rely on the first derivative of the output function, and ignore the second derivative. To assess parameter importance more accurately, a new parameter regularization method called Second Derivative Preserver (SDP), which takes advantage of the second derivative of the output function, is designed into MPGAN. Experiments demonstrate that MPGAN is applicable to multiple parameter regularization methods and that SDP achieves high accuracy in parameter importance.INDEX TERMS Catastrophic forgetting, generative adversarial network, parameter regularization methods.

Multiband VAE: Latent Space Partitioning for Knowledge Consolidation in Continual Learning

“…There are several works that train GANs in the continual learning scenarios either with memory replay [49] or regularization [4], with the extension to VAEGAN [22] in [53].…”