Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Yuheng, Qian, Bingshuo, Yuan, Caixia, Jiang, Huixing, Wang, Xiaojie
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912285024321536
author Lu, Yuheng
Qian, Bingshuo
Yuan, Caixia
Jiang, Huixing
Wang, Xiaojie
author_facet Lu, Yuheng
Qian, Bingshuo
Yuan, Caixia
Jiang, Huixing
Wang, Xiaojie
contents Large language models (LLMs) exhibit remarkable capabilities in natural language processing but face catastrophic forgetting when learning new tasks, where adaptation to a new domain leads to a substantial decline in performance on previous tasks. In this paper, we propose Controlled LoRA (CLoRA), a sub-space regularization method on LoRA structure. Aiming to reduce the scale of output change while introduce minimal constraint on model capacity, CLoRA imposes constraint on the direction of updating matrix's null space. Experimental results on one-stage LLM finetuning tasks and continual learning settings highlight the superority of CLoRA as a effective parameter efficient finetuning method with catastrophic forgetting mitigating.Further investigation for model parameters indicates that CLoRA effectively balances the trade-off between model capacity and degree of forgetting.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16801
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models
Lu, Yuheng
Qian, Bingshuo
Yuan, Caixia
Jiang, Huixing
Wang, Xiaojie
Computation and Language
Artificial Intelligence
Large language models (LLMs) exhibit remarkable capabilities in natural language processing but face catastrophic forgetting when learning new tasks, where adaptation to a new domain leads to a substantial decline in performance on previous tasks. In this paper, we propose Controlled LoRA (CLoRA), a sub-space regularization method on LoRA structure. Aiming to reduce the scale of output change while introduce minimal constraint on model capacity, CLoRA imposes constraint on the direction of updating matrix's null space. Experimental results on one-stage LLM finetuning tasks and continual learning settings highlight the superority of CLoRA as a effective parameter efficient finetuning method with catastrophic forgetting mitigating.Further investigation for model parameters indicates that CLoRA effectively balances the trade-off between model capacity and degree of forgetting.
title Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.16801