This paper studies the challenging continual learning (CL) setting of Class Incremental Learning (CIL). CIL learns a sequence of tasks consisting of disjoint sets of concepts or classes. At any time, a single model is built that can be applied to predict/classify test instances of any classes learned thus far without providing any task related information for each test instance. Although many techniques have been proposed for CIL, they are mostly empirical. It has been shown recently that a strong CIL system needs a strong within-task prediction (WP) and a strong out-of-distribution (OOD) detection for each task. However, it is still not known whether CIL is actually learnable. This paper shows that CIL is learnable. Based on the theory, a new CIL algorithm is also proposed. Experimental results demonstrate its effectiveness.

翻译：本文研究了类增量学习（CIL）这一具有挑战性的连续学习（CL）设定。CIL学习一系列由不相交的概念或类别集合构成的任务。在任何时刻，系统构建一个单一的模型，该模型可用于预测/分类迄今为止所学习的任何类别的测试实例，而无需为每个测试实例提供任何任务相关信息。尽管已有许多针对CIL的技术被提出，但它们大多基于经验方法。近期研究表明，一个强大的CIL系统需要具备强大的任务内预测（WP）能力以及针对每个任务的强大分布外（OOD）检测能力。然而，CIL是否真正可学习这一问题仍不明确。本文证明了CIL是可学习的，并基于该理论提出了一种新的CIL算法。实验结果验证了其有效性。