Catastrophic Forgetting Mitigation Through Plateau Phase Activity Profiling
This incremental improvement addresses a key challenge in continual learning for AI systems, enhancing their ability to learn sequentially without degrading past knowledge.
The paper tackles catastrophic forgetting in deep neural networks by proposing a method that tracks parameter activity during the final training plateau to identify flat loss landscape directions, achieving superior performance in balancing forgetting mitigation with new task learning.
Catastrophic forgetting in deep neural networks occurs when learning new tasks degrades performance on previously learned tasks due to knowledge overwriting. Among the approaches to mitigate this issue, regularization techniques aim to identify and constrain "important" parameters to preserve previous knowledge. In the highly nonconvex optimization landscape of deep learning, we propose a novel perspective: tracking parameters during the final training plateau is more effective than monitoring them throughout the entire training process. We argue that parameters that exhibit higher activity (movement and variability) during this plateau reveal directions in the loss landscape that are relatively flat, making them suitable for adaptation to new tasks while preserving knowledge from previous ones. Our comprehensive experiments demonstrate that this approach achieves superior performance in balancing catastrophic forgetting mitigation with strong performance on newly learned tasks.