Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation

Xiwen Wei, Guihong Li, Radu Marculescu

Keywords: Online Continual Learning, Catastrophic Forgetting, Vision Transformers (ViT), Low-Rank Adaptation (LoRA)

Abstract:

Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and privacy concerns inherent in rehearsal buffers. To tackle catastrophic forgetting, in this paper, we introduce Online-LoRA, a novel framework for task-free OCL. Online-LoRA allows to finetune pre-trained Vision Transformer (ViT) models in real-time to address the limitations of rehearsal buffers and leverage pre-trained models’ performance benefits. As the main contribution, our approach features a novel online weight regularization strategy to identify and consolidate important model parameters. Moreover, Online-LoRA leverages the training dynamics of loss values to enable the automatic recognition of the data distribution shifts. Extensive experiments across many task-free OCL scenarios and benchmark datasets demonstrate that Online-LoRA can be robustly adapted to various ViT architectures, while achieving better performance compared to SOTA methods.

Submission Number: 6