Active Learning for Continual Learning: Keeping the Past Alive in the Present
This addresses the challenge of balancing learning new tasks with retaining old knowledge in scenarios with costly annotations, though it is an incremental improvement over existing methods.
The paper tackles the problem of catastrophic forgetting in active continual learning by proposing AccuACL, a method that uses Fisher information for sample selection, resulting in a 23.8% increase in average accuracy and a 17.0% reduction in forgetting compared to baselines.
Continual learning (CL) enables deep neural networks to adapt to ever-changing data distributions. In practice, there may be scenarios where annotation is costly, leading to active continual learning (ACL), which performs active learning (AL) for the CL scenarios when reducing the labeling cost by selecting the most informative subset is preferable. However, conventional AL strategies are not suitable for ACL, as they focus solely on learning the new knowledge, leading to catastrophic forgetting of previously learned tasks. Therefore, ACL requires a new AL strategy that can balance the prevention of catastrophic forgetting and the ability to quickly learn new tasks. In this paper, we propose AccuACL, Accumulated informativeness-based Active Continual Learning, by the novel use of the Fisher information matrix as a criterion for sample selection, derived from a theoretical analysis of the Fisher-optimality preservation properties within the framework of ACL, while also addressing the scalability issue of Fisher information-based AL. Extensive experiments demonstrate that AccuACL significantly outperforms AL baselines across various CL algorithms, increasing the average accuracy and forgetting by 23.8% and 17.0%, respectively, on average.