paper-with-me

Papers

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance

2025-10-03 · Hao Zhang, Zhenjia Li, Runfeng Bao, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu arxiv

Parameter-Efficient Fine-Tuning (PEFT), especially Low-Rank Adaptation (LoRA), has emerged as a promising approach to fine-tuning large language models(LLMs) while reducing computational and memory overhead. However, LoRA assumes a uniform rank \textit{r} for each incremental matrix, not accounting for the varying significance of weight matrices across different modules and layers. AdaLoRA leverages Singular Value Decomposition (SVD) to parameterize updates and employs pruning of singular values to introduce dynamic rank allocation, thereby enhancing adaptability. However, during the training process, it often encounters issues of slow convergence speed and high computational overhead. To address this issue, we propose HyperAdaLoRA, a novel framework that accelerates the convergence of AdaLoRA by leveraging a hypernetwork. Instead of directly optimizing the components of Singular Value Decomposition $(P, Λ, Q)$, HyperAdaLoRA employs a hypernetwork based on attention mechanisms to dynamically generate these parameters. By pruning the outputs of the hypernetwork that generates the singular values, dynamic rank allocation is achieved. Comprehensive experiments on various datasets and models demonstrate that our method achieves faster convergence without sacrificing performance. Additionally, further extension experiments on other LoRA-based approaches validate the broad applicability of our method.

📄 PDF Abstract BibTeX arXiv:2510.02630

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs

2025-06-23 · Haseeb Ullah Khan Shinwari, Muhammad Usama

Conventional Low-Rank Adaptation (LoRA) methods employ a fixed rank, imposing uniform adaptation across transformer layers and attention heads despite their heterogeneous learning dynamics. This paper introduces Adaptive…

parameter-efficient fine-tuning

Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation

2025-05-17 · Prashant Shivaram Bhat, Shakib Yazdani, Elahe Arani, Bahram Zonooz

Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Parameter efficient fine tuning CL techniques…

Continual Learningparameter-efficient fine-tuning

CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models

2025-10-11 · Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao, Chen Liu 외 arxiv

Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods improve efficiency through low-rank updates, …

parameter-efficient fine-tuning

Statistical Inference for Rank Allocation in Low-Rank Adaptation

2026-07-22 · Yihang Gao, Vincent Y. F. Tan arxiv

Low-rank adaptation (LoRA) has become a widely used parameter-efficient fine-tuning method for large language models. Since different modules and layers may contribute unequally to downstream adaptation, allocating rank …

parameter-efficient fine-tuningNatural Language UnderstandingQuestion Answering

Post-Optimization Adaptive Rank Allocation for LoRA

2026-04-30 · Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith arxiv

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregar…

parameter-efficient fine-tuning