Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused by an ever-changing parameter space during the learning process. Additionally, continual learning does not assume the data stream to be stationary, typically resulting in catastrophic forgetting of previous knowledge. As a first, we introduce a system addressing both problems, where prototypes evolve continually in a shared latent space, enabling learning and prediction at any point in time. In contrast to the major body of work in continual learning, data streams are processed in an online fashion, without additional task-information, and an efficient memory scheme provides robustness to imbalanced data streams. Besides nearest neighbor based prediction, learning is facilitated by a novel objective function, encouraging cluster density about the class prototype and increased inter-class variance. Furthermore, the latent space quality is elevated by pseudo-prototypes in each batch, constituted by replay of exemplars from memory. As an additional contribution, we generalize the existing paradigms in continual learning to incorporate data incremental learning from data streams by formalizing a two-agent learner-evaluator framework. We obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.
翻译:在代表制学习中,已经很好地建立了能够代表阶级分布的典型特征。然而,通过流数据在线学习原型证明是一项艰巨的工作,因为其迅速过时,原因是学习过程中的参数空间不断变化。此外,持续学习并不假定数据流是静止的,通常会导致灾难性地忘记先前的知识。首先,我们引入一个处理这两个问题的系统,即原型在共享的潜在空间中不断演化,从而能够随时进行学习和预测。与不断学习的主要工作相比,数据流以在线方式处理,没有额外的任务信息,高效的记忆计划为不平衡的数据流提供了稳健性。除了最近的以邻居为基础的预测外,新的客观功能也为学习提供了便利,鼓励类原型的集群密度和增加的阶级间差异。此外,每个批次的隐性空间质量都由假的原型提高,这是从记忆中重现的表层。作为补充,我们概括了现有模式,即通过将数据流数据流的渐进式学习纳入数据流中,通过正式化两个代理人学习模式,包括高度的平流数据运行框架。