Continual learning (CL) aims to develop techniques by which a single model adapts to an increasing number of tasks encountered sequentially, thereby potentially leveraging learnings across tasks in a resource-efficient manner. A major challenge for CL systems is catastrophic forgetting, where earlier tasks are forgotten while learning a new task. To address this, replay-based CL approaches maintain and repeatedly retrain on a small buffer of data selected across encountered tasks. We propose Gradient Coreset Replay (GCR), a novel strategy for replay buffer selection and update using a carefully designed optimization criterion. Specifically, we select and maintain a "coreset" that closely approximates the gradient of all the data seen so far with respect to current model parameters, and discuss key strategies needed for its effective application to the continual learning setting. We show significant gains (2%-4% absolute) over the state-of-the-art in the well-studied offline continual learning setting. Our findings also effectively transfer to online / streaming CL settings, showing upto 5% gains over existing approaches. Finally, we demonstrate the value of supervised contrastive loss for continual learning, which yields a cumulative gain of up to 5% accuracy when combined with our subset selection strategy.
翻译:持续学习(CL) 旨在开发各种技术,使单一模式适应越来越多的相继工作,从而有可能以资源效率高的方式利用跨任务学习。 CL 系统面临的一个主要挑战是灾难性的忘记,因为先前的任务在学习新任务时被遗忘。要解决这个问题,基于重放的 CL 方法维持并反复重复在通过交叉任务选择的小型缓冲数据上。我们建议渐进式核心重播(GCR),这是一个利用精心设计的优化标准重新播放缓冲选择和更新的新型战略。具体地说,我们选择并保持一个“核心集”,密切接近到目前模型参数所看到的所有数据的梯度,并讨论将其有效应用到持续学习环境所需的关键战略。我们展示了在深思熟虑的离线持续学习中,艺术状态(2%-4%绝对值)的巨大收益。我们的结果还有效地转移到在线/流式 CL 设置中,显示现有方法的增益率达5%。最后,我们展示了在连续学习过程中受监督的对比性损失的价值,在连续学习过程中,在不断选择的分层中,将产生累积性战略的增益。