无需存储数据或任务边界，实现高效在线持续学习
Rehearsal-free and Task-free Online Continual Learning With Contrastive Prompt
- 用对比提示与神经记忆分类器结合，避免遗忘
- 在两个基准上达到领先性能，无需样本重放
- 适合隐私敏感场景，尤其适合无法划分任务的实时学习
持续学习的核心挑战是灾难性遗忘。由于在线持续学习（OCL）需单遍处理数据，难度更高。现有方法要么使用重放缓冲区存储样本，要么依赖任务边界与身份识别。但存储样本存在隐私风险，且实际场景中难以划分任务边界。为此，本文提出无需重放、无需任务标识的在线持续学习方法（F2OCL）。通过将提示学习与神经记忆分类器（NCM）结合，该方法在不存储数据、不依赖任务信息的前提下有效缓解遗忘问题。在两个基准数据集上的实验结果验证了其有效性。
原文摘要 · Abstract (English)
The main challenge of continual learning is \textit{catastrophic forgetting}. Because of processing data in one pass, online continual learning (OCL) is one of the most difficult continual learning scenarios. To address catastrophic forgetting in OCL, some existing studies use a rehearsal buffer to store samples and replay them in the later learning process, other studies do not store samples but assume a sequence of learning tasks so that the task identities can be explored. However, storing samples may raise data security or privacy concerns and it is not always possible to identify the boundaries between learning tasks in one pass of data processing. It motivates us to investigate rehearsal-free and task-free OCL (F2OCL). By integrating prompt learning with an NCM classifier, this study has effectively tackled catastrophic forgetting without storing samples and without usage of task boundaries or identities. The extensive experimental results on two benchmarks have demonstrated the effectiveness of the proposed method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。