Continual Learning with Low Rank Adaptation

Martin Wistuba, Prabhu Teja S, Lukas Balles, Giovanni Zappella

Keywords: continual learning, vision transformer, catastrophic forgetting

TL;DR: We scrutinize the use of prompt tuning in continual learning in favor of other options.

Abstract: 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.

Submission Number: 44