paper-with-me

Papers

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product

2025-08-01 · Paul Albert, Frederic Z. Zhang, Hemanth Saratchandran, Anton van den Hengel, Ehsan Abbasnejad arxiv

Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large pre-trained models. Amongst PEFT methods, low-rank adaptation (LoRA) has achieved notable success. However, recent studies have highlighted its limitations compared against full-rank alternatives, particularly when applied to multimodal and large language models. In this work, we present a quantitative comparison amongst full-rank and low-rank PEFT methods using a synthetic matrix approximation benchmark with controlled spectral properties. Our results confirm that LoRA struggles to approximate matrices with relatively flat spectrums or high frequency components -- signs of high effective ranks. To this end, we introduce KRAdapter, a novel PEFT algorithm that leverages the Khatri-Rao product to produce weight updates, which, by construction, tends to produce matrix product with a high effective rank. We demonstrate performance gains with KRAdapter on vision-language models up to 1B parameters and on large language models up to 8B parameters, particularly on unseen common-sense reasoning tasks. In addition, KRAdapter maintains the memory and compute efficiency of LoRA, making it a practical and robust alternative to fine-tune billion-scale parameter models.

📄 PDF Abstract BibTeX arXiv:2508.00230

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

2024-11-07 · Ayan Sengupta, Vaibhav Seth, Arinjay Pathak, Natraj Raman 외

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperp…

Natural Language Understandingparameter-efficient fine-tuningparameter estimation

Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance

2024-07-24 · Ao Shen, Qiang Wang, Zhiquan Lai, Xionglve Li 외

Large Language Models (LLMs) have demonstrated impressive performance across various domains. However, the enormous number of model parameters makes fine-tuning challenging, significantly limiting their application and d…

Quantization

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning

2026-01-12 · Yongkang Liu, Xing Li, Mengjie Zhao, Shanru Zhang 외 arxiv

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to…

parameter-efficient fine-tuning

IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuning

2023-08-23 · Feiyu Zhang, Liangzhi Li, JunHao Chen, Zhouqiang Jiang 외

With the increasing size of pre-trained language models (PLMs), fine-tuning all the parameters in the model is not efficient, especially when there are a large number of downstream tasks, which incur significant training…

parameter-efficient fine-tuning

MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models

2024-01-15 · Divyanshu Aggarwal, Ashutosh Sathe, Ishaan Watts, Sunayana Sitaram

Parameter Efficient Finetuning (PEFT) has emerged as a viable solution for improving the performance of Large Language Models (LLMs) without requiring massive resources and compute. Prior work on multilingual evaluation …