Continual Learning (CL) is the research field addressing learning without forgetting when the data distribution is not static. This paper studies spurious features' influence on continual learning algorithms. We show that continual learning algorithms solve tasks by selecting features that are not generalizable. Our experiments highlight that continual learning algorithms face two related problems: (1) spurious features and (2) local spurious features. The first one is due to a covariate shift between training and testing data, while the second is due to the limited access to data at each training step. We study (1) through a consistent set of continual learning experiments varying spurious correlation amount and data distribution support. We show that (2) is a major cause of performance decrease in continual learning along with catastrophic forgetting. This paper presents a different way of understanding performance decrease in continual learning by highlighting the influence of (local) spurious features in algorithms capabilities.

翻译：持续学习(CL)是处理学习的研究领域,不忘数据分布不是静止的。本文研究虚假的特征对持续学习算法的影响。我们显示,持续学习算法通过选择无法概括的特征来解决任务。我们的实验强调,持续学习算法面临两个相关问题:(1) 虚假特征和(2) 本地的虚假特征。第一个原因是培训和测试数据之间发生共变变化,第二个原因是每个培训阶段获得数据的机会有限。我们研究(1) 通过一套一致的不断学习实验,研究(1) 不同的虚假相关数量和数据分布支持。我们表明,(2) 持续学习与灾难性的遗忘是持续学习业绩下降的一个主要原因。本文通过突出(本地)虚假特征在算法能力上的影响,提出了一种不同的理解持续学习业绩下降的方法。