Continual Learning with Strong Experience Replay
This addresses forgetting in continual learning for AI systems, but it is incremental as it builds on existing experience replay techniques.
The paper tackles the problem of forgetting in continual learning by proposing Strong Experience Replay (SER), which uses future experiences mimicked on current data to preserve knowledge, and it surpasses state-of-the-art methods by a noticeable margin on multiple image classification datasets.
Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal-based strategy, which optimizes the model with current training data and a subset of old samples stored in a memory buffer. To further reduce forgetting, recent approaches extend ER with various techniques, such as model regularization and memory sampling. However, the prediction consistency between the new model and the old one on current training data has been seldom explored, resulting in less knowledge preserved when few previous samples are available. To address this issue, we propose a CL method with Strong Experience Replay (SER), which additionally utilizes future experiences mimicked on the current training data, besides distilling past experience from the memory buffer. In our method, the updated model will produce approximate outputs as its original ones, which can effectively preserve the acquired knowledge. Experimental results on multiple image classification datasets show that our SER method surpasses the state-of-the-art methods by a noticeable margin.