C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xin, Bai, Liang, Yang, Xian, Liang, Jiye
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916628996816896
author Zhang, Xin
Bai, Liang
Yang, Xian
Liang, Jiye
author_facet Zhang, Xin
Bai, Liang
Yang, Xian
Liang, Jiye
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
Zhang, Xin
Bai, Liang
Yang, Xian
Liang, Jiye
Machine Learning
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.
title C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
topic Machine Learning
url https://arxiv.org/abs/2502.17920