论文标题
D-CBRS：考虑持续学习的类内多样性
D-CBRS: Accounting For Intra-Class Diversity in Continual Learning
论文作者
论文摘要
持续学习 - 从一系列学习经验中积累知识 - 是一个重要但充满挑战的问题。在此范式中，由于看到其他数据，该模型的先前遇到实例的性能可能会大大下降。在处理类不平衡数据时，忘记会进一步加剧。先前的工作提出了基于重播的方法，旨在通过智能存储未来重播的实例来减少遗忘。尽管类平衡储层抽样（CBR）在处理不平衡数据方面已经成功，但尚未考虑类内的多样性，因为假设类的每个实例都同样有用。我们提出了不同的cbrs（D-CBRS），这是一种算法，使我们可以在存储内存中的实例中考虑在类别中。我们的结果表明，D-CBR的表现优于最先进的内存管理，持续学习算法，这些算法具有相当大的类内多样性的数据集。
Continual learning -- accumulating knowledge from a sequence of learning experiences -- is an important yet challenging problem. In this paradigm, the model's performance for previously encountered instances may substantially drop as additional data are seen. When dealing with class-imbalanced data, forgetting is further exacerbated. Prior work has proposed replay-based approaches which aim at reducing forgetting by intelligently storing instances for future replay. Although Class-Balancing Reservoir Sampling (CBRS) has been successful in dealing with imbalanced data, the intra-class diversity has not been accounted for, implicitly assuming that each instance of a class is equally informative. We present Diverse-CBRS (D-CBRS), an algorithm that allows us to consider within class diversity when storing instances in the memory. Our results show that D-CBRS outperforms state-of-the-art memory management continual learning algorithms on data sets with considerable intra-class diversity.
