paper-with-me

Papers

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

2024-05-05 · Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu, Bingzhe Wu, Liang Chen, Jia Li

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the weight change, i.e., $\Delta W=BA$. Despite LoRA's progress, it faces storage challenges when handling extensive customization adaptations or larger base models. In this work, we aim to further compress trainable parameters by enjoying the powerful expressiveness of the Fourier transform. Specifically, we introduce FourierFT, which treats $\Delta W$ as a matrix in the spatial domain and learns only a small fraction of its spectral coefficients. With the trained spectral coefficients, we implement the inverse discrete Fourier transform to recover $\Delta W$. Empirically, our FourierFT method shows comparable or better performance with fewer parameters than LoRA on various tasks, including natural language understanding, natural language generation, instruction tuning, and image classification. For example, when performing instruction tuning on the LLaMA2-7B model, FourierFT surpasses LoRA with only 0.064M trainable parameters, compared to LoRA's 33.5M. Our code is released at \url{https://github.com/Chaos96/fourierft}.

📄 PDF Abstract BibTeX arXiv:2405.03003

Code (1)

chaos96/fourierft 공식 구현 pytorch

Tasks

image-classificationImage ClassificationNatural Language Understandingparameter-efficient fine-tuningText Generation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform

2025-06-26 · Maxime Leiber, Yosra Marnissi, Axel Barrau, Sylvain Meignen 외

The short-time Fourier transform (STFT) is widely used for analyzing non-stationary signals. However, its performance is highly sensitive to its parameters, and manual or heuristic tuning often yields suboptimal results.…

Parameter-Efficient Fine-Tuning via Selective Discrete Cosine Transform

2024-10-09 · Yixian Shen, Qi Bi, Jia-Hong Huang, Hongyi Zhu 외

In the era of large language models, parameter-efficient fine-tuning (PEFT) has been extensively studied. However, these approaches usually rely on the space domain, which encounters storage challenges especially when ha…

parameter-efficient fine-tuning

Circular Convolution and Product Theorem for Affine Discrete Fractional Fourier Transform

2020-10-19 · Amir R. Nafchi, Eric Hamke, Cristina Pereyra, Ramiro Jordan

The Fractional Fourier Transform is a ubiquitous signal processing tool in basic and applied sciences. The Fractional Fourier Transform generalizes every property and application of the Fourier Transform. Despite the pra…

FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models

2026-04-02 · Juyong Jiang, Fan Wang, Hong Qi, Sunghun Kim 외 arxiv

Parameter-efficient fine-tuning (PEFT) has emerged as a crucial paradigm for adapting large language models (LLMs) under constrained computational budgets. However, standard PEFT methods often struggle in multi-task fine…

parameter-efficient fine-tuning

LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning

2025-02-05 · Zhekai Du, Yinjie Min, Jingjing Li, Ke Lu 외

Low-rank adaptation (LoRA) has become a prevalent method for adapting pre-trained large language models to downstream tasks. However, the simple low-rank decomposition form may constrain the hypothesis space. To address …

parameter-efficient fine-tuning