# Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings

arXiv: https://arxiv.org/abs/2211.05717 · HTML: https://mlsanity.com/paper/2211.05717/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 10 Nov 2022.

## Builds on (most cited first, 9 of 9)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [Collaborative Machine Learning with Incentive-Aware Model Rewards](https://mlsanity.com/paper/2010.12797/) (2020)
- [Privacy-Preserving Machine Learning: Methods, Challenges and Directions](https://mlsanity.com/paper/2108.04417/) (2021)
- [Deep Dimension Reduction for Supervised Representation Learning](https://mlsanity.com/paper/2006.05865/) (2020)
- [House price estimation from visual and textual features](https://mlsanity.com/paper/1609.08399/) (2016)
- [AutoGAN-based Dimension Reduction for Privacy Preservation](https://mlsanity.com/paper/1902.10799/) (2019)

## Built on by (most cited first, 2 of 2)

- [Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach](https://mlsanity.com/paper/2309.04427/) (2023)
- [Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning](https://mlsanity.com/paper/2603.15842/) (2026)

## Abstract (arXiv)

Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organization must assure that sensitive data remains private throughout the whole ML pipeline, i.e., training and inference phases. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data. Thus, organizations can share the data representation to increase machine learning models' performance in scenarios with more than one data source for a shared predictive downstream task.