Semi-supervised Learning with Multi-Head Co-Training


  • Mingcai Chen Nanjing University
  • Yuntao Du Nanjing University
  • Yi Zhang Nanjing University
  • Shuwei Qian Nanjing University
  • Chongjun Wang Nanjing University



Machine Learning (ML)


Co-training, extended from self-training, is one of the frameworks for semi-supervised learning. Without natural split of features, single-view co-training works at the cost of training extra classifiers, where the algorithm should be delicately designed to prevent individual classifiers from collapsing into each other. To remove these obstacles which deter the adoption of single-view co-training, we present a simple and efficient algorithm Multi-Head Co-Training. By integrating base learners into a multi-head structure, the model is in a minimal amount of extra parameters. Every classification head in the unified model interacts with its peers through a “Weak and Strong Augmentation” strategy, in which the diversity is naturally brought by the strong data augmentation. Therefore, the proposed method facilitates single-view co-training by 1). promoting diversity implicitly and 2). only requiring a small extra computational overhead. The effectiveness of Multi-Head Co-Training is demonstrated in an empirical study on standard semi-supervised learning benchmarks.




How to Cite

Chen, M., Du, Y., Zhang, Y., Qian, S., & Wang, C. (2022). Semi-supervised Learning with Multi-Head Co-Training. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6278-6286.



AAAI Technical Track on Machine Learning I