2 papers
cs.LG2023
G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks
Anchun Gui, Jinqiang Ye, Han Xiao
It has become a popular paradigm to transfer the knowledge of large-scale pre-trained models to various downstream tasks via fine-tuning the entire model parameters. However, with…
cs.CL2023
HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model Adaptation
Anchun Gui, Han Xiao
To fully leverage the advantages of large-scale pre-trained language models (PLMs) on downstream tasks, it has become a ubiquitous adaptation paradigm to fine-tune the entire param…