# Embedding-Based Federated Data Sharing via Differentially Private Conditional VAEs

arXiv: https://arxiv.org/abs/2507.02671 · HTML: https://mlsanity.com/paper/2507.02671/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Vision Transformers are Robust Learners](https://mlsanity.com/paper/2105.07581/) (2021)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [Generative models improve fairness of medical classifiers under distribution shifts](https://mlsanity.com/paper/2304.09218/) (2023)
- [Personalized Federated Learning through Local Memorization](https://mlsanity.com/paper/2111.09360/) (2021)
- [FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification](https://mlsanity.com/paper/2206.13803/) (2022)
- [DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder](https://mlsanity.com/paper/2211.11591/) (2022)
- [FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation](https://mlsanity.com/paper/2307.10507/) (2023)
- [A Systematic Review of Federated Generative Models](https://mlsanity.com/paper/2405.16682/) (2024)
- [Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)](https://mlsanity.com/paper/2211.11434/) (2022)
- [Privacy-preserving datasets by capturing feature distributions with Conditional VAEs](https://mlsanity.com/paper/2408.00639/) (2024)

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

- [FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing](https://mlsanity.com/paper/2601.00785/) (2026)
- [LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations](https://mlsanity.com/paper/2609.12364/) (2026)

## Abstract (arXiv)

Deep Learning (DL) has revolutionized medical imaging, yet its adoption is constrained by data scarcity and privacy regulations, limiting access to diverse datasets. Federated Learning (FL) enables decentralized training but suffers from high communication costs and is often restricted to a single downstream task, reducing flexibility. We propose a data-sharing method via Differentially Private (DP) generative models. By adopting foundation models, we extract compact, informative embeddings, reducing redundancy and lowering computational overhead. Clients collaboratively train a Differentially Private Conditional Variational Autoencoder (DP-CVAE) to model a global, privacy-aware data distribution, supporting diverse downstream tasks. Our approach, validated across multiple feature extractors, enhances privacy, scalability, and efficiency, outperforming traditional FL classifiers while ensuring differential privacy. Additionally, DP-CVAE produces higher-fidelity embeddings than DP-CGAN while requiring 5× fewer parameters.