Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
This work addresses the challenge of maintaining old knowledge while learning new tasks in continual learning, which is important for AI systems that need to adapt over time, though it appears incremental as it builds on existing methods like GANs and neural masking.
The paper tackles the problem of continual learning by introducing Dynamic Generative Memory (DGM), a synaptic plasticity-driven framework that uses conditional generative adversarial networks with neural masking and dynamic network expansion, achieving competitive performance on visual classification tasks in continual class-incremental setups.
Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking. Specifically, we evaluate two variants of neural masking: applied to (i) layer activations and (ii) to connection weights directly. Furthermore, we propose a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks. The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks.