Pith. sign in

REVIEW 1 cited by

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.03003 v1 pith:XJ54KQLK submitted 2024-05-05 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords lorafourierftparametersdeltafouriertrainabletransformcoefficients
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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., $\Delta W=BA$. 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}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation

    cs.CV 2025-02 conditional novelty 3.0 of 10

    SSH fine-tunes large models by learning sparse Hartley-spectrum coefficients selected by energy of the pretrained weights, matching or beating LoRA and FourierFT with fewer parameters.

Pith tools