Lifelong learning, also referred to as continual learning, is the problem of training an AI agent continuously while also preventing it from forgetting its previously acquired knowledge. Most of the existing methods primarily focus on lifelong learning within a static environment and lack the ability to mitigate forgetting in a quickly-changing dynamic environment. Streaming lifelong learning is a challenging setting of lifelong learning with the goal of continuous learning in a dynamic non-stationary environment without forgetting. We introduce a novel approach to lifelong learning, which is streaming, requires a single pass over the data, can learn in a class-incremental manner, and can be evaluated on-the-fly (anytime inference). To accomplish these, we propose virtual gradients for continual representation learning to prevent catastrophic forgetting and leverage an exponential-moving-average-based semantic memory to further enhance performance. Extensive experiments on diverse datasets demonstrate our method's efficacy and superior performance over existing methods.

翻译：终身学习（亦称持续学习）旨在持续训练人工智能代理的同时防止其遗忘先前获取的知识。现有方法主要聚焦于静态环境中的终身学习，缺乏在快速变化的动态环境中缓解遗忘的能力。流式终身学习是终身学习中的一个具有挑战性的设定，其目标是在动态非平稳环境中实现持续学习且不遗忘知识。我们提出了一种新颖的终身学习方法，该方法具有流式特性：仅需对数据单次遍历，能以类增量方式学习，并可进行实时评估（即时推理）。为实现这些目标，我们提出了用于持续表示学习的虚拟梯度以防止灾难性遗忘，并利用基于指数移动平均的语义记忆进一步提升性能。在多个不同数据集上的大量实验表明，我们的方法优于现有方法，展现出卓越的有效性。