SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.03003 · ICML · 2024

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

Jia Li, Ziqi Gao, Bingzhe Wu, Liang Chen, Aochuan Chen, Zijing Liu, Qichao Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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., ∆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 ∆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 ∆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 https: //github.com/Chaos96/fourierft.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.03003")
get_code_for_paper("2405.03003")
have("2405.03003")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.03003.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.03003.svg)](https://syntology.ai/paper/2405.03003)

Connect an agent — have() is free.