CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
It addresses the problem of preserving knowledge in AI models during continuous learning, offering a domain-specific improvement over existing replay-based methods.
This paper tackles catastrophic forgetting in continual learning by proposing CORE, a cognitive replay method that adaptively allocates replay buffer space and selects representative data, achieving an average accuracy of 37.95% on split-CIFAR10, which is 6.52% higher than the best baseline.
This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based methods treat every task and data sample equally and thus can not fully exploit the potential of the replay buffer. In response, we propose COgnitive REplay (CORE), which draws inspiration from human cognitive review processes. CORE includes two key strategies: Adaptive Quantity Allocation and Quality-Focused Data Selection. The former adaptively modulates the replay buffer allocation for each task based on its forgetting rate, while the latter guarantees the inclusion of representative data that best encapsulates the characteristics of each task within the buffer. Our approach achieves an average accuracy of 37.95% on split-CIFAR10, surpassing the best baseline method by 6.52%. Additionally, it significantly enhances the accuracy of the poorest-performing task by 6.30% compared to the top baseline. Code is available at https://github.com/sterzhang/CORE.