In continual learning, the learner learns multiple tasks in sequence, with
data being acquired only once for each task. Catastrophic forgetting is a major
challenge to continual learning. To reduce forgetting, some existing
rehearsal-based methods use episodic memory to replay samples of previous
tasks. However, in the process of knowledge integration when learning a new
task, this strategy also suffers from catastrophic forgetting due to an
imbalance between old and new knowledge. To address this problem, we propose a
novel replay strategy called Manifold Expansion Replay (MaER). We argue that
expanding the implicit manifold of the knowledge representation in the episodic
memory helps to improve the robustness and expressiveness of the model. To this
end, we propose a greedy strategy to keep increasing the diameter of the
implicit manifold represented by the knowledge in the buffer during memory
management. In addition, we introduce Wasserstein distance instead of cross
entropy as distillation loss to preserve previous knowledge. With extensive
experimental validation on MNIST, CIFAR10, CIFAR100, and TinyImageNet, we show
that the proposed method significantly improves the accuracy in continual
learning setup, outperforming the state of the arts.

我们提出了一种新的回放策略，称为 Manifold Expansion Replay (MaER)，通过扩展知识表示的隐含流形，改善模型的鲁棒性和表达能力，以解决在学习新任务过程中由于老知识和新知识之间不平衡导致的灾难性遗忘问题。我们通过对 MNIST、CIFAR10、CIFAR100 和 TinyImageNet 进行广泛实验验证，表明提出的方法在继续学习设置中显著提高了准确性，优于现有技术水平。