SAFE：面向预训练模型持续学习的慢速与快速参数高效微调
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
AI总结：
针对持续学习中预训练模型参数微调不充分及增量会话冻结参数导致塑性不足的问题，提出SAFE框架，通过迁移损失、固定慢速参数更新快速参数及熵聚合策略，在七个基准上超越现有方法。
摘要：
持续学习旨在从数据流中增量获取新概念，同时抵抗对先前知识的遗忘。随着强大的预训练模型（PTMs）的兴起，人们越来越关注利用这些基础模型来训练增量学习系统，而非从零开始学习。现有工作通常将预训练模型视为强初始点，并在第一个会话中直接应用参数高效微调（PET）以适应下游任务。在后续会话中，大多数方法冻结模型参数以解决遗忘问题。然而，将PET直接应用于下游数据无法充分挖掘预训练模型中的固有知识。此外，在增量会话中冻结参数阻碍了模型对第一个会话中未涵盖的新概念的塑性。为解决上述问题，我们提出了一个慢速与快速参数高效微调（SAFE）框架。具体而言，为了继承基础模型的通用知识，我们通过测量预训练模型与应用PET的模型之间的相关性，引入了一个迁移损失函数。在第一个会话中校准后，慢速高效微调参数能够捕获更具信息量的特征，从而提升对即将到来类别的泛化能力。此外，为了进一步融入新概念，我们通过固定慢速高效微调参数并持续更新快速参数，在稳定性与塑性之间取得平衡。具体来说，我们提出了一种带有特征对齐的交叉分类损失，以避免灾难性遗忘。在推理过程中，我们引入了一种基于熵的聚合策略，以动态利用慢速与快速学习器之间的互补性。在七个基准数据集上的大量实验验证了我们方法的有效性，显著超越了现有最先进水平。
英文摘要：
Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning systems using these foundation models, rather than learning from scratch. Existing works often view PTMs as a strong initial point and directly apply parameter-efficient tuning (PET) in the first session for adapting to downstream tasks. In the following sessions, most methods freeze model parameters for tackling forgetting issues. However, applying PET directly to downstream data cannot fully explore the inherent knowledge in PTMs. Additionally, freezing the parameters in incremental sessions hinders models' plasticity to novel concepts not covered in the first session. To solve the above issues, we propose a Slow And Fast parameter-Efficient tuning (SAFE) framework. In particular, to inherit general knowledge from foundation models, we include a transfer loss function by measuring the correlation between the PTM and the PET-applied model. After calibrating in the first session, the slow efficient tuning parameters can capture more informative features, improving generalization to incoming classes. Moreover, to further incorporate novel concepts, we strike a balance between stability and plasticity by fixing slow efficient tuning parameters and continuously updating the fast ones. Specifically, a cross-classification loss with feature alignment is proposed to circumvent catastrophic forgetting. During inference, we introduce an entropy-based aggregation strategy to dynamically utilize the complementarity in the slow and fast learners. Extensive experiments on seven benchmark datasets verify the effectiveness of our method by significantly surpassing the state-of-the-art.
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。
