论文标题
基于梯度的编辑记忆示例，用于在线无任务持续学习
Gradient-based Editing of Memory Examples for Online Task-free Continual Learning
论文作者
论文摘要
我们探索无任务的持续学习（CL），其中训练模型以避免在没有明确任务边界或身份的情况下灾难性遗忘。在无任务CL上的许多努力中，一个著名的方法家族是基于内存的基于内存和重播培训示例的部分。但是，由于CL模型不断更新，随着时间的推移，存储的可见示例的实用程序可能会随着时间的推移而减少。在这里，我们建议基于梯度的内存编辑（GMED），这是一个通过梯度更新在连续输入空间中编辑存储的示例的框架，以创建更多的“挑战”示例以进行重播。 GMED编辑的示例与其未经编辑的形式相似，但在即将到来的模型更新中可以增加损失，从而使未来在克服灾难性遗忘方面更有效。通过构造，可以与其他基于内存的CL算法一起无缝地应用GMED，以带来进一步的改进。实验验证了GMED的有效性，而我们的最佳方法在六个数据集中有五分之五明显优于基准和先前的最新方法。代码可以在https://github.com/ink-usc/gmed上找到。
We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting in the absence of explicit task boundaries or identities. Among many efforts on task-free CL, a notable family of approaches are memory-based that store and replay a subset of training examples. However, the utility of stored seen examples may diminish over time since CL models are continually updated. Here, we propose Gradient based Memory EDiting (GMED), a framework for editing stored examples in continuous input space via gradient updates, in order to create more "challenging" examples for replay. GMED-edited examples remain similar to their unedited forms, but can yield increased loss in the upcoming model updates, thereby making the future replays more effective in overcoming catastrophic forgetting. By construction, GMED can be seamlessly applied in conjunction with other memory-based CL algorithms to bring further improvement. Experiments validate the effectiveness of GMED, and our best method significantly outperforms baselines and previous state-of-the-art on five out of six datasets. Code can be found at https://github.com/INK-USC/GMED.
