Despite rapid advancements in lifelong learning (LLL) research, a large body of research mainly focuses on improving the performance in the existing \textit{static} continual learning (CL) setups. These methods lack the ability to succeed in a rapidly changing \textit{dynamic} environment, where an AI agent needs to quickly learn new instances in a `single pass' from the non-i.i.d (also possibly temporally contiguous/coherent) data streams without suffering from catastrophic forgetting. For practical applicability, we propose a novel lifelong learning approach, which is streaming, i.e., a single input sample arrives in each time step, single pass, class-incremental, and subject to be evaluated at any moment. To address this challenging setup and various evaluation protocols, we propose a Bayesian framework, that enables fast parameter update, given a single training example, and enables any-time inference. We additionally propose an implicit regularizer in the form of snap-shot self-distillation, which effectively minimizes the forgetting further. We further propose an effective method that efficiently selects a subset of samples for online memory rehearsal and employs a new replay buffer management scheme that significantly boosts the overall performance. Our empirical evaluations and ablations demonstrate that the proposed method outperforms the prior works by large margins.

翻译：尽管终身学习（LLL）研究取得了快速进展，大量研究主要侧重于改进现有"静态"持续学习（CL）设置下的性能。这些方法缺乏在快速变化的"动态"环境中成功运行的能力，在该环境中，AI代理需要从非独立同分布（也可能具有时间连续/一致性）的数据流中，以"单次通过"方式快速学习新实例，同时避免灾难性遗忘。为了实现实际应用，我们提出了一种新颖的终身学习方法，该方法具有流式特征（即每个时间步到达单个输入样本）、单次通过、类增量特性，并可在任意时刻进行评估。为了应对这一具有挑战性的设置及多种评估协议，我们提出了一种贝叶斯框架，该框架能够在给定单个训练样本的情况下实现快速参数更新，并支持任意时刻推理。我们还提出了一种以快照自蒸馏形式的隐式正则化器，有效进一步减少了遗忘。此外，我们提出了一种高效方法，能够选择样本子集进行在线记忆重放，并采用了一种新的重放缓冲区管理策略，显著提升了整体性能。我们的实证评估和消融实验表明，所提方法大幅优于先前工作。