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.
@article{arxiv.2405.21050,
title = {Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models},
author = {Xinxi Zhang and Song Wen and Ligong Han and Felix Juefei-Xu and Akash Srivastava and Junzhou Huang and Hao Wang and Molei Tao and Dimitris N. Metaxas},
journal= {arXiv preprint arXiv:2405.21050},
year = {2024}
}