基于低秩适应的持续学习
Continual Learning with Low Rank Adaptation
AI总结：
本文提出CoLoR，将低秩适应（LoRA）应用于持续学习，在领域增量学习基准上以与提示微调方法相当的参数效率取得了最先进性能。
摘要：
近期使用预训练Transformer的工作表明，在利用下游目标问题的数据进行微调时，其性能表现令人印象深刻。然而，当数据特征发生变化时，这些模型难以保持原有性能。本文聚焦于持续学习，即更新一个预训练Transformer，使其在新数据上表现良好，同时保持其在先前训练数据上的性能。早期工作主要通过受提示微调启发的方法来解决这一问题。我们质疑这一选择，并研究了低秩适应（LoRA）在持续学习中的适用性。在一系列领域增量学习基准上，我们基于LoRA的解决方案CoLoR取得了最先进的性能，同时仍与基于提示微调的方法一样具有参数效率。
英文摘要：
Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristics changes. In this paper, we focus on continual learning, where a pre-trained transformer is updated to perform well on new data, while retaining its performance on data it was previously trained on. Earlier works have tackled this primarily through methods inspired from prompt tuning. We question this choice, and investigate the applicability of Low Rank Adaptation (LoRA) to continual learning. On a range of domain-incremental learning benchmarks, our LoRA-based solution, CoLoR, yields state-of-the-art performance, while still being as parameter efficient as the prompt tuning based methods.
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。
