G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networks

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 the growth of model scale and the rising number of downstream tasks, this paradigm inevitably meets the challenges in te...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-05
Hauptverfasser:	Gui, Anchun, Ye, Jinqiang, Han, Xiao
Format:	Artikel
Sprache:	eng
Schlagworte:	Adapters Benchmarks Knowledge management Mathematical models Natural language processing Optimization Parameters Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!