paper-with-me

홈 › Papers

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

2024-10-22 · Yuheng Lu, Bingshuo Qian, Caixia Yuan, Huixing Jiang, Xiaojie Wang

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 subspace 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 null space. Experimental results on commonly used LLM finetuning tasks reveal that CLoRA significantly outperforms existing LoRA subsequent methods on both in-domain and outdomain evaluations, highlighting 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.

📄 PDF Abstract BibTeX arXiv:2410.16801

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Subspace Geometry Governs Catastrophic Forgetting in Low-Rank Adaptation

2026-02-10 · Brady Steele arxiv

Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for adapting large pre-trained models, yet its behavior under continual learning remains poorly understood. We present a geometric theory character…

parameter-efficient fine-tuningContinual Learning

Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift

2026-05-06 · Jonathan R. Landers arxiv

We study long-horizon deployment of a frozen predictor under dynamic covariate shift. A time-domain Poincare inequality first reduces temporal risk volatility to derivative energy. A Jacobian-velocity theorem then suppli…

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation

2025-05-24 · Jian Liang, Wenke Huang, Xianda Guo, Guancheng Wan 외

Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize …

Mixture-of-Experts

iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models

2026-05-19 · Xuezhi Cui, Dongbo Zhou, Wang Guo, Zeyuan Wang 외 arxiv

Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning isolated modules per task leads to paramete…

parameter-efficient fine-tuningContinual Learning

Random Subspace Cubic-Regularization Methods, with Applications to Low-Rank Functions

2025-01-16 · Coralia Cartis, Zhen Shao, Edward Tansley

We propose and analyze random subspace variants of the second-order Adaptive Regularization using Cubics (ARC) algorithm. These methods iteratively restrict the search space to some random subspace of the parameters, con…

ARC