Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay
This addresses the problem of forgetting past tasks in deep networks for researchers and practitioners in continual learning, but it is incremental as it builds on existing experience replay methods.
The paper tackles catastrophic forgetting in sequential multitask learning by learning a generative model that couples current and past tasks through a discriminative embedding space, and demonstrates theoretically and empirically that this framework learns a shared distribution to avoid forgetting.
Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address this challenge by learning a generative model that couples the current task to the past learned tasks through a discriminative embedding space. We learn an abstract level generative distribution in the embedding that allows the generation of data points to represent the experience. We sample from this distribution and utilize experience replay to avoid forgetting and simultaneously accumulate new knowledge to the abstract distribution in order to couple the current task with past experience. We demonstrate theoretically and empirically that our framework learns a distribution in the embedding that is shared across all task and as a result tackles catastrophic forgetting.