# Reinforced Co-Training

arXiv: https://arxiv.org/abs/1804.06035 · HTML: https://mlsanity.com/paper/1804.06035/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2018.

## Built on by (most cited first, 7 of 7)

- [Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems](https://mlsanity.com/paper/2108.12589/) (2021)
- [On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation](https://mlsanity.com/paper/2109.07591/) (2021)
- [Unsupervised Conversation Disentanglement through Co-Training](https://mlsanity.com/paper/2109.03199/) (2021)
- [Semi-Supervised Text Classification via Self-Pretraining](https://mlsanity.com/paper/2109.15300/) (2021)
- [CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite](https://mlsanity.com/paper/2403.11873/) (2024)
- [Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning](https://mlsanity.com/paper/2410.06118/) (2024)
- [RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving](https://mlsanity.com/paper/2505.11893/) (2025)

## Abstract (arXiv)

Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on prediction confidence to augment the training. However, the selection of samples in existing co-training methods is based on a predetermined policy, which ignores the sampling bias between the unlabeled and the labeled subsets, and fails to explore the data space. In this paper, we propose a novel method, Reinforced Co-Training, to select high-quality unlabeled samples to better co-train on. More specifically, our approach uses Q-learning to learn a data selection policy with a small labeled dataset, and then exploits this policy to train the co-training classifiers automatically. Experimental results on clickbait detection and generic text classification tasks demonstrate that our proposed method can obtain more accurate text classification results.