处理在线持续学习中的跨任务类判别问题
Dealing with Cross-Task Class Discrimination in Online Continual Learning
AI总结：
本文指出了类增量学习中的跨任务类判别（CTCD）挑战，并发现回放方法存在动态训练偏差问题，为此提出了一种基于梯度的自适应优化目标，在在线持续学习中动态解决该问题并取得更优效果。
摘要：
现有的持续学习（CL）研究几乎将灾难性遗忘（CF）视为唯一的挑战。本文指出了类增量学习（CIL）中的另一个挑战，我们称之为跨任务类判别（CTCD），即如何在无法（或仅能有限）访问旧任务数据的情况下，在新任务的类与旧任务的类之间建立决策边界。基于回放的方法隐式且部分地处理了CTCD问题。回放方法会保存少量来自先前任务的数据（回放数据）。当一批当前任务数据到达时，系统会联合训练新数据和部分采样的回放数据。由于保存的数据量较小，回放数据使系统能够部分学习新类与旧类之间的决策边界。然而，本文认为回放方法还存在动态训练偏差问题，这降低了回放数据在解决CTCD问题上的有效性。我们提出了一种具有基于梯度的自适应方法的新型优化目标，以在在线CL过程中动态处理该问题。实验结果表明，新方法在在线CL中取得了更好的结果。
英文摘要：
Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination (CTCD),~i.e., how to establish decision boundaries between the classes of the new task and old tasks with no (or limited) access to the old task data. CTCD is implicitly and partially dealt with by replay-based methods. A replay method saves a small amount of data (replay data) from previous tasks. When a batch of current task data arrives, the system jointly trains the new data and some sampled replay data. The replay data enables the system to partially learn the decision boundaries between the new classes and the old classes as the amount of the saved data is small. However, this paper argues that the replay approach also has a dynamic training bias issue which reduces the effectiveness of the replay data in solving the CTCD problem. A novel optimization objective with a gradient-based adaptive method is proposed to dynamically deal with the problem in the online CL process. Experimental results show that the new method achieves much better results in online CL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
