# FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing

arXiv: https://arxiv.org/abs/2601.00785 · HTML: https://mlsanity.com/paper/2601.00785/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 2 Jan 2026.

## Builds on (most cited first, 30 of 34)

- [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)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (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)
- [Evaluating Gradient Inversion Attacks and Defenses in Federated Learning](https://mlsanity.com/paper/2112.00059/) (2021)
- [Salvaging Federated Learning by Local Adaptation](https://mlsanity.com/paper/2002.04758/) (2020)
- [Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective](https://mlsanity.com/paper/2012.06043/) (2020)
- [Generative models improve fairness of medical classifiers under distribution shifts](https://mlsanity.com/paper/2304.09218/) (2023)
- [Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage](https://mlsanity.com/paper/2203.15696/) (2022)
- [A Framework for Evaluating Gradient Leakage Attacks in Federated Learning](https://mlsanity.com/paper/2004.10397/) (2020)
- [Personalized Federated Learning through Local Memorization](https://mlsanity.com/paper/2111.09360/) (2021)
- [Privacy-preserving Federated Learning based on Multi-key Homomorphic Encryption](https://mlsanity.com/paper/2104.06824/) (2021)
- [FedTP: Federated Learning by Transformer Personalization](https://mlsanity.com/paper/2211.01572/) (2022)
- [PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage](https://mlsanity.com/paper/2108.04725/) (2021)
- [Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning](https://mlsanity.com/paper/2202.05318/) (2022)
- [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)
- [Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning](https://mlsanity.com/paper/2309.05505/) (2023)
- [SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge Intelligence](https://mlsanity.com/paper/2203.08176/) (2022)

## Abstract (arXiv)

Federated data sharing promises utility without centralizing raw data, yet existing embedding-level generators struggle under non-IID client heterogeneity and provide limited formal protection against gradient leakage. We propose FedHypeVAE, a differentially private, hypernetwork-driven framework for synthesizing embedding-level data across decentralized clients. Building on a conditional VAE backbone, we replace the single global decoder and fixed latent prior with client-aware decoders and class-conditional priors generated by a shared hypernetwork from private, trainable client codes. This bi-level design personalizes the generative layerrather than the downstream modelwhile decoupling local data from communicated parameters. The shared hypernetwork is optimized under differential privacy, ensuring that only noise-perturbed, clipped gradients are aggregated across clients. A local MMD alignment between real and synthetic embeddings and a Lipschitz regularizer on hypernetwork outputs further enhance stability and distributional coherence under non-IID conditions. After training, a neutral meta-code enables domain agnostic synthesis, while mixtures of meta-codes provide controllable multi-domain coverage. FedHypeVAE unifies personalization, privacy, and distribution alignment at the generator level, establishing a principled foundation for privacy-preserving data synthesis in federated settings. Code: github.com/sunnyinAI/FedHypeVAE