Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning

TL;DR

This paper introduces the C&F framework that proactively creates and identifies flat regions in the loss landscape for each task, enhancing continual learning by reducing catastrophic forgetting and improving knowledge retention.

Contribution

The novel C&F framework builds flat training spaces in advance for each task, focusing on the pre-task learning phase to improve continual learning performance.

Findings

Achieves state-of-the-art results in continual learning tasks.

Effectively preserves previous knowledge while learning new tasks.

Compatible with other continual learning methods.

Abstract

Catastrophic forgetting remains a critical challenge in the field of continual learning, where neural networks struggle to retain prior knowledge while assimilating new information. Most existing studies emphasize mitigating this issue only when encountering new tasks, overlooking the significance of the pre-task phase. Therefore, we shift the attention to the current task learning stage, presenting a novel framework, C&F (Create and Find Flatness), which builds a flat training space for each task in advance. Specifically, during the learning of the current task, our framework adaptively creates a flat region around the minimum in the loss landscape. Subsequently, it finds the parameters' importance to the current task based on their flatness degrees. When adapting the model to a new task, constraints are applied according to the flatness and a flat space is simultaneously prepared for the impending task. We theoretically demonstrate the consistency between the created and found flatness. In this manner, our framework not only accommodates ample parameter space for learning new tasks but also preserves the preceding knowledge of earlier tasks. Experimental results exhibit C&F's state-of-the-art performance as a standalone continual learning approach and its efficacy as a framework incorporating other methods. Our work is available at https://github.com/Eric8932/Create-and-Find-Flatness.