Private Semi-supervised Knowledge Transfer for Deep Learning from Noisy Labels
This work addresses privacy concerns in publishing models trained on sensitive data, offering an incremental enhancement to the PATE framework for better utility in semi-supervised learning.
The paper tackles the problem of noisy labels in private knowledge transfer for deep learning, proposing PATE++ which integrates noisy label training mechanisms and a GAN structure to improve student model accuracy, achieving improvements on Fashion-MNIST and SVHN datasets.
Deep learning models trained on large-scale data have achieved encouraging performance in many real-world tasks. Meanwhile, publishing those models trained on sensitive datasets, such as medical records, could pose serious privacy concerns. To counter these issues, one of the current state-of-the-art approaches is the Private Aggregation of Teacher Ensembles, or PATE, which achieved promising results in preserving the utility of the model while providing a strong privacy guarantee. PATE combines an ensemble of "teacher models" trained on sensitive data and transfers the knowledge to a "student" model through the noisy aggregation of teachers' votes for labeling unlabeled public data which the student model will be trained on. However, the knowledge or voted labels learned by the student are noisy due to private aggregation. Learning directly from noisy labels can significantly impact the accuracy of the student model. In this paper, we propose the PATE++ mechanism, which combines the current advanced noisy label training mechanisms with the original PATE framework to enhance its accuracy. A novel structure of Generative Adversarial Nets (GANs) is developed in order to integrate them effectively. In addition, we develop a novel noisy label detection mechanism for semi-supervised model training to further improve student model performance when training with noisy labels. We evaluate our method on Fashion-MNIST and SVHN to show the improvements on the original PATE on all measures.