RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning
Yaqing Wang, Xin Tian, Haoyi Xiong, Yueyang Li, Zeyu Chen, Sheng Guo, Dejing Dou
Abstract
Pre-trained language models (PLMs) can provide a good starting point for downstream applications. However, it is difficult to generalize PLMs to new tasks given a few labeled samples. In this work, we show that Relation Graph augmented Learning (RGL) can improve the performance of few-shot natural language understanding tasks. During learning, RGL constructs a relation graph based on the label consistency between samples in the same batch, and learns to solve the resultant node classification and link prediction problems on the relation graph. In this way, RGL fully exploits the limited supervised information, which can boost the tuning effectiveness. Extensive experimental results show that RGL consistently improves the performance of prompt-based tuning strategies.
BibTeX
@inproceedings{wang-etal-2022-rgl,
title = "{RGL}: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning",
author = "Wang, Yaqing and
Tian, Xin and
Xiong, Haoyi and
Li, Yueyang and
Chen, Zeyu and
Guo, Sheng and
Dou, Dejing",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.81/",
doi = "10.18653/v1/2022.findings-naacl.81",
pages = "1078--1084"
}