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

• URL: http://arxiv.org/abs/2502.06820v2
• Date: Tue, 29 Apr 2025 09:28:40 GMT
• Title: LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning
• Authors: Zhekai Du, Yinjie Min, Jingjing Li, Ke Lu, Changliang Zou, Liuhua Peng, Tingjin Chu, Mingming Gong,
• Abstract summary: Location-aware Cosine Adaptation (LoCA) is a novel frequency-domain parameter-efficient fine-tuning method based on Discrete inverse Cosine Transform (iDCT)<n>Our analysis reveals that frequency-domain decomposition with carefully selected frequency components can surpass the expressivity of traditional low-rank-based methods.<n>Experiments on diverse language and vision fine-tuning tasks demonstrate that LoCA offers enhanced parameter efficiency while maintains computational feasibility comparable to low-rank-based methods.
• Score: 47.77830360814755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 this limitation, we introduce Location-aware Cosine Adaptation (LoCA), a novel frequency-domain parameter-efficient fine-tuning method based on inverse Discrete Cosine Transform (iDCT) with selective locations of learnable components. We begin with a comprehensive theoretical comparison between frequency-domain and low-rank decompositions for fine-tuning pre-trained large models. Our analysis reveals that frequency-domain decomposition with carefully selected frequency components can surpass the expressivity of traditional low-rank-based methods. Furthermore, we demonstrate that iDCT offers a more efficient implementation compared to inverse Discrete Fourier Transform (iDFT), allowing for better selection and tuning of frequency components while maintaining equivalent expressivity to the optimal iDFT-based adaptation. By employing finite-difference approximation to estimate gradients for discrete locations of learnable coefficients on the DCT spectrum, LoCA dynamically selects the most informative frequency components during training. Experiments on diverse language and vision fine-tuning tasks demonstrate that LoCA offers enhanced parameter efficiency while maintains computational feasibility comparable to low-rank-based methods.

Related papers

• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• Parameter-Efficient Fine-Tuning via Selective Discrete Cosine Transform [10.565509997395504]
  We propose a novel Selective Discrete Cosine Transformation (sDCTFT) fine-tuning scheme to push this frontier. Its general idea is to exploit the superior energy compaction and decorrelation properties of DCT. Experiments on four benchmark datasets demonstrate the superior accuracy, reduced computational cost, and lower storage requirements.
  arXiv  Detail & Related papers  (2024-10-09T16:07:42Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Frequency Domain-based Dataset Distillation [17.02955182740882]
  We present FreD, a novel parameterization method for dataset distillation. FreD employs frequency-based transforms to optimize the frequency representations of each data instance.
  arXiv  Detail & Related papers  (2023-11-15T09:46:30Z)
• Learning Unnormalized Statistical Models via Compositional Optimization [73.30514599338407]
  Noise-contrastive estimation(NCE) has been proposed by formulating the objective as the logistic loss of the real data and the artificial noise. In this paper, we study it a direct approach for optimizing the negative log-likelihood of unnormalized models.
  arXiv  Detail & Related papers  (2023-06-13T01:18:16Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)
• Deep Frequency Filtering for Domain Generalization [55.66498461438285]
  Deep Neural Networks (DNNs) have preferences for some frequency components in the learning process. We propose Deep Frequency Filtering (DFF) for learning domain-generalizable features. We show that applying our proposed DFF on a plain baseline outperforms the state-of-the-art methods on different domain generalization tasks.
  arXiv  Detail & Related papers  (2022-03-23T05:19:06Z)
• Learning Frequency Domain Approximation for Binary Neural Networks [68.79904499480025]
  We propose to estimate the gradient of sign function in the Fourier frequency domain using the combination of sine functions for training BNNs. The experiments on several benchmark datasets and neural architectures illustrate that the binary network learned using our method achieves the state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2021-03-01T08:25:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.