Controller-Guided Partial Label Consistency Regularization with Unlabeled Data
DOI:
https://doi.org/10.1609/aaai.v38i14.29484Keywords:
ML: Multi-class/Multi-label Learning & Extreme Classification, ML: Multi-instance/Multi-view Learning, ML: Semi-Supervised LearningAbstract
Partial label learning (PLL) learns from training examples each associated with multiple candidate labels, among which only one is valid. In recent years, benefiting from the strong capability of dealing with ambiguous supervision and the impetus of modern data augmentation methods, consistency regularization-based PLL methods have achieved a series of successes and become mainstream. However, as the partial annotation becomes insufficient, their performances drop significantly. In this paper, we leverage easily accessible unlabeled examples to facilitate the partial label consistency regularization. In addition to a partial supervised loss, our method performs a controller-guided consistency regularization at both the label-level and representation-level with the help of unlabeled data. To minimize the disadvantages of insufficient capabilities of the initial supervised model, we use the controller to estimate the confidence of each current prediction to guide the subsequent consistency regularization. Furthermore, we dynamically adjust the confidence thresholds so that the number of samples of each class participating in consistency regularization remains roughly equal to alleviate the problem of class-imbalance. Experiments show that our method achieves satisfactory performances in more practical situations, and its modules can be applied to existing PLL methods to enhance their capabilities.Downloads
Published
2024-03-24
How to Cite
Wang, Q.-W., Zhao, B., Zhu, M., Li, T., Liu, Z., & Xia, S.-T. (2024). Controller-Guided Partial Label Consistency Regularization with Unlabeled Data. Proceedings of the AAAI Conference on Artificial Intelligence, 38(14), 15571-15579. https://doi.org/10.1609/aaai.v38i14.29484
Issue
Section
AAAI Technical Track on Machine Learning V