Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. We introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.
Code (1)
Tasks
Computational Efficiencyparameter-efficient fine-tuningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ReCoLoRA: Spectrum-Aware Recursive Consolidation for Continual LLM Fine-Tuning
Parameter-efficient fine-tuning adapts a large language model to one task cheaply, but across a task sequence LoRA-style methods keep stacking low-rank updates on the same frozen weight, so each new task tends to overwri…
parameter-efficient fine-tuningSMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to…
parameter-efficient fine-tuningS2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods based on Fourier transforms have furthe…
parameter-efficient fine-tuningNaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of full fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) has become …
parameter-efficient fine-tuningMathematical ReasoningCode GenerationGIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models
Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models…