C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
This addresses the challenge of efficient and scalable continual learning for pre-trained models in domains like NLP and computer vision, though it is an incremental improvement over existing LoRA methods.
The paper tackles the problem of adapting pre-trained models to dynamic learning environments by proposing C-LoRA, a continual learning extension of LoRA that uses a learnable routing matrix to manage parameter updates across tasks, achieving state-of-the-art accuracy and parameter efficiency on benchmarks.
Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine-tuning approaches excel in static environments but struggle in dynamic learning due to reliance on multiple adapter modules, increasing overhead and complicating inference. We propose Continual Low-Rank Adaptation (C-LoRA), a novel extension of LoRA for continual learning. C-LoRA uses a learnable routing matrix to dynamically manage parameter updates across tasks, ensuring efficient reuse of learned subspaces while enforcing orthogonality to minimize interference and forgetting. Unlike existing approaches that require separate adapters for each task, C-LoRA enables a integrated approach for task adaptation, achieving both scalability and parameter efficiency in sequential learning scenarios. C-LoRA achieves state-of-the-art accuracy and parameter efficiency on benchmarks while providing theoretical insights into its routing matrix's role in retaining and transferring knowledge, establishing a scalable framework for continual learning.