# Improving Differentially Private Models with Active Learning

arXiv: https://arxiv.org/abs/1910.01177 · HTML: https://mlsanity.com/paper/1910.01177/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training](https://mlsanity.com/paper/2306.08173/) (2023)
- [Private Semi-supervised Knowledge Transfer for Deep Learning from Noisy Labels](https://mlsanity.com/paper/2211.01628/) (2022)
- [Differentially Private Active Learning: Balancing Effective Data Selection and Privacy](https://mlsanity.com/paper/2410.00542/) (2024)

## Abstract (arXiv)

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees, but applying these techniques to neural networks can severely degrade model performance. This performance reduction is an obstacle to deploying private models in the real world. In this work, we improve the performance of DP models by fine-tuning them through active learning on public data. We introduce two new techniques - DIVERSEPUBLIC and NEARPRIVATE - for doing this fine-tuning in a privacy-aware way. For the MNIST and SVHN datasets, these techniques improve state-of-the-art accuracy for DP models while retaining privacy guarantees.