Self-Training with Differentiable Teacher
Simiao Zuo, Yue Yu, Liang Chen, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha · Findings of the Association for Computational Linguistics: NAACL 2022 · 2022
Self-training achieves enormous success in various semi-supervised and weakly-supervised learning tasks.The method can be interpreted as a teacher-student framework, where the teacher generates pseudo-labels, and the student makes predictions.The two models are updated alternatingly.However, such a straightforward alternating update rule leads to training instability.This is because a small change in the teacher may result in a significant change in the student.To address this issue, we propose DRIFT, short for differentiable self-training, that treats teacher-student as a Stackelberg game.In this game, a leader is always in a more advantageous position than a follower.In selftraining, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels.Therefore, we treat the student as the leader and the teacher as the follower.The leader procures its advantage by acknowledging the follower's strategy, which involves differentiable pseudolabels and differentiable sample weights.Consequently, the leader-follower interaction can be effectively captured via Stackelberg gradient, obtained by differentiating the follower's strategy.Experimental results on semi-and weakly-supervised classification and named entity recognition tasks show that our model outperforms existing approaches by large margins.