Chengwei Sun

DWTSG: Parameter-Efficient Fine-Tuning of Large Pre-trained Models via Discrete Wavelet Transform and Subband Guidance

Fully fine-tuning large pre-trained models for each downstream task is impractical due to prohibitive memory, computation, and storage costs. Although parameter-efficient fine-tuning (PEFT) methods address this issue, leading methods like LoRA still exhibit linear scaling of trainable parameters wit