Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets

• URL: http://arxiv.org/abs/2505.12532v2
• Date: Tue, 03 Jun 2025 21:46:26 GMT
• Title: Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets
• Authors: Ahmet Bilican, M. Akın Yılmaz, A. Murat Tekalp, R. Gökberk Cinbiş,
• Abstract summary: We propose Wavelet Fine-Tuning (WaveFT), a novel PEFT method that learns highly sparse updates in the wavelet domain of residual matrices.<n>WaveFT allows precise control of trainable parameters, offering fine-grained capacity adjustment and excelling with remarkably low parameter count.
• Score: 5.161899009439659
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Efficiently adapting large foundation models is critical, especially with tight compute and memory budgets. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA offer limited granularity and effectiveness in few-parameter regimes. We propose Wavelet Fine-Tuning (WaveFT), a novel PEFT method that learns highly sparse updates in the wavelet domain of residual matrices. WaveFT allows precise control of trainable parameters, offering fine-grained capacity adjustment and excelling with remarkably low parameter count, potentially far fewer than LoRA's minimum, ideal for extreme parameter-efficient scenarios. Evaluated on personalized text-to-image generation using Stable Diffusion XL as baseline, WaveFT significantly outperforms LoRA and other PEFT methods, especially at low parameter counts; achieving superior subject fidelity, prompt alignment, and image diversity.

Related papers

• FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts [47.35092228595656]
  FLoE is a novel PEFT framework that introduces two key innovations: (i) a Fisher information-guided importance scoring mechanism to dynamically identify task-critical transformer layers for MoE-based low-rank adaptation, enabling sparse adapter deployment; and (ii) a Bayesian optimization-driven rank allocator that automatically determines optimal LoRA ranks on specific datasets without exhaustive grid search.<n>Experiments across diverse LLMs and benchmarks reveal that FLoE achieves impressive efficiency-accuracy trade-offs, making FLoE particularly advantageous in resource-constrained environments that necessitate rapid adaptation.
  arXiv  Detail & Related papers  (2025-05-31T10:27:08Z)
• Parameter-Efficient Fine-Tuning with Column Space Projection [4.379304291229695]
  We propose PiCa, the first theoretically grounded PEFT method based on the spectral properties of fine-tuned weights.<n>We show that PiCa achieves the state-of-the-art performance compared to existing PEFT methods.
  arXiv  Detail & Related papers  (2025-05-26T16:52:40Z)
• FISH-Tuning: Enhancing PEFT Methods with Fisher Information [3.9274736061387854]
  FISH Mask is a selection-based PEFT technique that identifies a critical subset of pre-trained parameters using approximate Fisher information.<n>We propose textbfFISH-Tuning, a novel approach that incorporates FISH Mask into such PEFT methods, including LoRA, Adapter, and their variants.
  arXiv  Detail & Related papers  (2025-04-05T04:05:55Z)
• Quantum-PEFT: Ultra parameter-efficient fine-tuning [46.145294417722184]
  Quantum-PEFT exploits an underlying full-rank yet surprisingly parameter efficient quantum unitary parameterization.<n>We show that Quantum-PEFT achieves vanishingly smaller number of trainable parameters than the lowest-rank LoRA as dimensions grow.<n>We apply Quantum-PEFT to several transfer learning benchmarks in language and vision, demonstrating significant advantages in parameter efficiency.
  arXiv  Detail & Related papers  (2025-03-07T14:01:25Z)
• Sparsity May Be All You Need: Sparse Random Parameter Adaptation [7.269130161558109]
  Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size.<n>We propose reducing the number of trainable parameters by randomly selecting a small proportion of the model parameters to train on.
  arXiv  Detail & Related papers  (2025-02-21T22:23:16Z)
• Sparse Gradient Compression for Fine-Tuning Large Language Models [58.44973963468691]
  Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models.<n>High memory costs associated with fine-tuning remain a significant challenge, especially as models increase in size.<n>We propose sparse compression gradient (SGC) to address these limitations.
  arXiv  Detail & Related papers  (2025-02-01T04:18:28Z)
• 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)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.<n>We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.<n>Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models [18.877891285367216]
  We introduce $textID3$, a novel selective PEFT method that calculates parameter importance continually.<n>We analytically show that $textID3$ reduces the number of gradient updates by a factor of two, enhancing computational efficiency.
  arXiv  Detail & Related papers  (2024-08-26T17:58:53Z)
• Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning [38.80020737321214]
  We propose a framework for efficient parameter fine-tuning (PEFT) based on structured unrestricted-rank matrices (SURM)<n>SURMs achieve 5-7% accuracy gains on various image classification tasks while replacing low-rank matrices in LoRA.<n>It also results in up to 12x reduction of the number of parameters in adapters (with virtually no loss in quality) on the GLUE benchmark.
  arXiv  Detail & Related papers  (2024-06-25T17:26:05Z)
• ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections [59.839926875976225]
  We propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections. In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters.
  arXiv  Detail & Related papers  (2024-05-30T17:26:02Z)
• From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers [52.199303258423306]
  We propose a novel density loss that encourages higher activation sparsity in pre-trained models. Our proposed method, textbfDEFT, can consistently reduce activation density by up to textbf44.94% on RoBERTa$_mathrmLarge$ and by textbf53.19% (encoder density) and textbf90.60% (decoder density) on Flan-T5$_mathrmXXL$.
  arXiv  Detail & Related papers  (2024-02-02T21:25:46Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)
• Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning [91.5113227694443]
  We propose a novel visual. sensuous-aware fine-Tuning (SPT) scheme. SPT allocates trainable parameters to task-specific important positions. Experiments on a wide range of downstream recognition tasks show that our SPT is complementary to the existing PEFT methods.
  arXiv  Detail & Related papers  (2023-03-15T12:34:24Z)

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.