May, 2024
TAGA:基于图和文本相互转换的自监督学习
TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations
Zheng Zhang, Yuntong Hu, Bo Pan, Chen Ling, Liang Zhao
TL;DRText-And-Graph Multi-View Alignment (TAGA) is a self-supervised learning framework that integrates Text-Attributed Graphs (TAGs), enabling efficient training and strong performance in zero-shot and few-shot scenarios across multiple datasets.