Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
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}.
Code (1)
Tasks
image-classificationImage ClassificationNatural Language Understandingparameter-efficient fine-tuningText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learnable Adaptive Time-Frequency Representation via Differentiable Short-Time Fourier Transform
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
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-tuningCircular Convolution and Product Theorem for Affine Discrete Fractional Fourier Transform
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
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-tuningLoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning
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