Contrastive Learning at the Relation and Event Level for Rumor Detection
Yingrui Xu, Jingyuan Hu, Jingguo Ge, Yulei Wu, Tong Li, Hui Li
Abstract
Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Learning (RECL) framework for rumor detection to address the above issue. Specifically, we present both the relation-level and event-level augmentation strategies to generate contrastive samples, which capture both the semantics revealed by repost relations and the structural features of rumor events. Moreover, contrastive learning tasks are devised to generate informative graph representations by utilizing self-supervision signals of unlabeled data. Extensive experimental results on real-world datasets demonstrate the effectiveness of our model, especially with limited labeled data.
BibTeX
@inproceedings{icassp2023_contrastivelearn,
title = {Contrastive Learning at the Relation and Event Level for Rumor Detection},
author = {Yingrui Xu and Jingyuan Hu and Jingguo Ge and Yulei Wu and Tong Li and Hui Li},
booktitle = {ICASSP 2023},
year = {2023}
}