AatMatch: Adaptive Adversarial Training in Semi-Supervised Learning Based on Data-Driven Decision-Making Models
Kuan Li, Qianzhi Lian, Can Gao, Fuyong Zhang · Systems · 2023
Data-driven decision-making is the process of using data to inform your decision-making process and validate a course of action before committing to it. The quality of unlabeled data in real-world scenarios presents challenges for semi-supervised learning. Effectively leveraging unlabeled data for learning is challenging due to the need for labeled information, while the scarcity of labeled data requires efficient and flexible data augmentation methods. To address these challenges, this paper proposes the AatMatch algorithm, which uses a momentum model, coarse learning, and adversarial training to generate adversarial examples for different classes. The algorithm sets the threshold for generating pseudo-labels and reinforces the results with adversarial perturbations based on evaluation results. In addition, a more refined learning strategy for unlabeled data is adjusted by setting adaptive weights based on the confidence of each unlabeled data point, thereby mitigating the adverse effects of low-confidence unlabeled data on the model. Experimental evaluations on several datasets, including CIFAR-10, CIFAR-100, and SVHN, demonstrate the effectiveness of the proposed AatMatch algorithm in semi-supervised learning. Specifically, the algorithm achieves the lowest error rates for multiple scenarios on these datasets.