# Differentially Private Transferrable Deep Learning with Membership-Mappings

arXiv: https://arxiv.org/abs/2105.04615 · HTML: https://mlsanity.com/paper/2105.04615/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 10 May 2021.

## Builds on (most cited first, 16 of 16)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising](https://mlsanity.com/paper/1805.06530/) (2018)
- [Differentially Private Mixture of Generative Neural Networks](https://mlsanity.com/paper/1709.04514/) (2017)
- [Efficient Learning of Domain-invariant Image Representations](https://mlsanity.com/paper/1301.3224/) (2013)
- [Learning an Invariant Hilbert Space for Domain Adaptation](https://mlsanity.com/paper/1611.08350/) (2016)
- [Optimal Bayesian Transfer Learning](https://mlsanity.com/paper/1801.00857/) (2018)
- [Optimal Noise-Adding Mechanism in Additive Differential Privacy](https://mlsanity.com/paper/1809.10224/) (2018)
- [Membership-Mappings for Data Representation Learning: Measure Theoretic Conceptualization](https://mlsanity.com/paper/2104.07060/) (2021)
- [Representation Transfer for Differentially Private Drug Sensitivity Prediction](https://mlsanity.com/paper/1901.10227/) (2019)
- [Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models](https://mlsanity.com/paper/1812.03123/) (2018)

## Built on by (most cited first, 5 of 5)

- [Transfer Learning In Differential Privacy's Hybrid-Model](https://mlsanity.com/paper/2201.12018/) (2022)
- [On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach](https://mlsanity.com/paper/2304.01300/) (2023)
- [Membership-Mappings for Practical Secure Distributed Deep Learning](https://mlsanity.com/paper/2204.05765/) (2022)
- [Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent](https://mlsanity.com/paper/2407.04335/) (2024)
- [Information Theoretic Evaluation of Privacy-Leakage, Interpretability, and Transferability for Trustworthy AI](https://mlsanity.com/paper/2106.06046/) (2021)

## Abstract (arXiv)

This paper considers the problem of differentially private semi-supervised transfer and multi-task learning. The notion of membership-mapping has been developed using measure theory basis to learn data representation via a fuzzy membership function. An alternative conception of deep autoencoder, referred to as Conditionally Deep Membership-Mapping Autoencoder (CDMMA), is considered for transferrable deep learning. Under practice-oriented settings, an analytical solution for the learning of CDMMA can be derived by means of variational optimization. The paper proposes a transfer and multi-task learning approach that combines CDMMA with a tailored noise adding mechanism to achieve a given level of privacy-loss bound with the minimum perturbation of the data. Numerous experiments were carried out using MNIST, USPS, Office, and Caltech256 datasets to verify the competitive robust performance of the proposed methodology.