Lifelong Twin Generative Adversarial Networks
This addresses the issue of catastrophic forgetting for researchers and practitioners in lifelong learning and generative modeling, though it appears incremental as it builds on existing GAN and knowledge distillation techniques.
The paper tackles the problem of catastrophic forgetting in generative models by proposing Lifelong Twin GANs (LT-GANs) with a Lifelong Adversarial Knowledge Distillation (LAKD) approach, enabling continuous learning across multiple tasks without forgetting previous ones.
In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs). LT-GANs learns a sequence of tasks from several databases and its architecture consists of three components: two identical generators, namely the Teacher and Assistant, and one Discriminator. In order to allow for the LT-GANs to learn new concepts without forgetting, we introduce a new lifelong training approach, namely Lifelong Adversarial Knowledge Distillation (LAKD), which encourages the Teacher and Assistant to alternately teach each other, while learning a new database. This training approach favours transferring knowledge from a more knowledgeable player to another player which knows less information about a previously given task.