Recently, continual learning (CL) has gained significant interest because it enables deep learning models to acquire new knowledge without forgetting previously learnt information. However, most existing works require knowing the task identities and boundaries, which is not realistic in a real context. In this paper, we address a more challenging and realistic setting in CL, namely the Task-Free Continual Learning (TFCL) in which a model is trained on non-stationary data streams with no explicit task information. To address TFCL, we introduce an evolved mixture model whose network architecture is dynamically expanded to adapt to the data distribution shift. We implement this expansion mechanism by evaluating the probability distance between the knowledge stored in each mixture model component and the current memory buffer using the Hilbert Schmidt Independence Criterion (HSIC). We further introduce two simple dropout mechanisms to selectively remove stored examples in order to avoid memory overload while preserving memory diversity. Empirical results demonstrate that the proposed approach achieves excellent performance.
翻译:最近,持续学习(CL)引起了很大的兴趣,因为它使深层次学习模式能够在不忘记以往所学到的信息的情况下获得新知识。然而,大多数现有工作需要了解任务特性和界限,这在现实中是不现实的。在本文件中,我们处理的是CL中更具挑战性和现实性的环境,即无任务持续学习(TFCL),在这种环境中,对非静止数据流进行了培训,但没有明确的任务信息。为了处理TFCL,我们引入了一种进化的混合模式,其网络结构正在动态扩展,以适应数据分配的转变。我们通过使用希尔伯特施密特独立标准(Hilbert Schmich独立标准)评估每个混合模式组成部分所储存的知识与当前记忆缓冲之间的概率距离来实施这一扩展机制。我们进一步引入了两种简单的辍学机制,以便有选择地删除存储的实例,以避免记忆超载,同时保持记忆的多样性。经验性结果表明,拟议的方法取得了出色的业绩。