超越提示学习：面向高效无排练持续学习的持续适配器
Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning
AI总结：
针对无排练持续学习中预训练模型域差距导致提示匹配不准的问题，提出含可扩展适配器层、缩放平移模块及正交损失的C-ADA方法，在性能和训练速度上均超越现有SOTA，且在域增量场景下具备通用性。
摘要：
无排练持续学习（Rehearsal-Free Continual Learning, RFCL）问题旨在不存储任何旧样本和原型的前提下，持续学习新知识同时防止旧知识遗忘。最新方法以大规模预训练模型为骨干网络，利用键-查询匹配生成可训练提示来学习新知识。然而，预训练数据集与下游数据集之间存在域差距，直接使用预训练模型生成查询时，很容易导致键-查询匹配的提示选择不准确，阻碍新知识的学习。\n因此，本文针对RFCL任务提出了一种超越提示学习的方法，名为持续适配器（Continual Adapter, C-ADA）。该方法主要由可参数扩展的持续适配器层（continual adapter layer, CAL）以及与预训练模型并行的缩放平移（scaling and shifting, S&S）模块组成。C-ADA为每个任务灵活扩展CAL中的特定权重以学习新知识，同时冻结旧权重以保留先验知识，从而避免键-查询匹配带来的匹配误差和操作低效问题。为缩小域差距，C-ADA采用S&S模块将特征空间从预训练数据集迁移到下游数据集。此外，我们提出了一种正交损失来缓解新旧知识之间的相互干扰。\n我们的方法在性能和训练速度上均实现了显著提升，优于当前最先进（state-of-the-art, SOTA）方法。此外，我们在域增量学习场景下开展了实验，结果同样超越了SOTA，证明了该方法在不同设置下的通用性。
英文摘要：
The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale pre-trained models as the backbone and use key-query matching to generate trainable prompts to learn new knowledge. However, the domain gap between the pre-training dataset and the downstream datasets can easily lead to inaccuracies in key-query matching prompt selection when directly generating queries using the pre-trained model, which hampers learning new knowledge. Thus, in this paper, we propose a beyond prompt learning approach to the RFCL task, called Continual Adapter (C-ADA). It mainly comprises a parameter-extensible continual adapter layer (CAL) and a scaling and shifting (S&S) module in parallel with the pre-trained model. C-ADA flexibly extends specific weights in CAL to learn new knowledge for each task and freezes old weights to preserve prior knowledge, thereby avoiding matching errors and operational inefficiencies introduced by key-query matching. To reduce the gap, C-ADA employs an S&S module to transfer the feature space from pre-trained datasets to downstream datasets. Moreover, we propose an orthogonal loss to mitigate the interaction between old and new knowledge. Our approach achieves significantly improved performance and training speed, outperforming the current state-of-the-art (SOTA) method. Additionally, we conduct experiments on domain-incremental learning, surpassing the SOTA, and demonstrating the generality of our approach in different settings.
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。
