A debiased self-training framework with graph self-supervised pre-training aided for semi-supervised rumor detection

Yuhan Qiao, Chaoqun Cui, Yiying Wang, Caiyan Jia

Abstract: Highlights•A self-training framework for semi-supervised rumor detection is proposed.•Graph self-supervised pre-training is employed to alleviate confirmation bias.•Self-adaptive thresholds are designed to generate reliable pseudo-labels.•The proposed model surpasses prior elaborate models in semi-supervised settings.