F Zhang, L Li, J Chen, Z Jiang, B Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
With the increasing size of pre-trained language models (PLMs), fine-tuning all the parameters in the model is not efficient, especially when there are a large number of …
Z Liu, Y Xu, Y Xu, Q Qian, H Li, X Ji… - Advances in Neural …, 2022 - proceedings.neurips.cc
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies …
Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc …
Among the widely used parameter-efficient finetuning (PEFT) methods, LoRA and its variants have gained considerable popularity because of avoiding additional inference …
Fine-tuning pre-trained deep networks on a small dataset is an important component in the deep learning pipeline. A critical problem in fine-tuning is how to avoid over-fitting when …
L Cai, Z An, C Yang, Y Yan, Y Xu - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Abstract We proposed a Prior Gradient Mask Guided Pruning-aware Fine-Tuning (PGMPF) framework to accelerate deep Convolutional Neural Networks (CNNs). In detail, the …
Abstract Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only …
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of …
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always …