Private Synthetic Data Meets Ensemble Learning
When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and real data. In this paper, we introduce a new ensemble strategy for training downstream models, with the goal of enhancing their performance when used on real data. We generate multiple synthetic datasets by applying a differential privacy (DP) mechanism several times in parallel and then ensemble the downstream models trained on these datasets. While each synthetic dataset might deviate more from the real data distribution, they collectively increase sample diversity. This may enhance the robustness of downstream models against distribution shifts. Our extensive experiments reveal that while ensembling does not enhance downstream performance (compared with training a single model) for models trained on synthetic data generated by marginal-based or workload-based DP mechanisms, our proposed ensemble strategy does improve the performance for models trained using GAN-based DP mechanisms in terms of both accuracy and calibration of downstream models.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityEnsemble LearningSimilar Papers 제목 키워드 기반
Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between h…
Privacy PreservingTransfer LearningScalable Differentially Private Data Generation via Private Aggregation of Teacher Ensembles
We present a novel approach named G-PATE for training differentially private data generator. The generator can be used to produce synthetic datasets with strong privacy guarantee while preserving high data utility. Our a…
PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech application…
Generative Adversarial NetworkKeyword SpottingPrivacy PreservingDifferentially Private Synthetic Data: Applied Evaluations and Enhancements
Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differentially private data synthesis protects …
BIG-bench Machine LearningConcept Drift Detection using Ensemble of Integrally Private Models
Deep neural networks (DNNs) are one of the most widely used machine learning algorithm. DNNs requires the training data to be available beforehand with true labels. This is not feasible for many real-world problems where…
Drift Detection