← Back to Papers
Key Insights
- A shared hypernetwork generates client‑specific VAE decoders and class‑conditional latent priors from lightweight private codes, enabling personalization without exposing raw data.
- Differential‑privacy is enforced at the hypernetwork level by clipping and adding Gaussian noise to aggregated gradients, protecting against gradient‑based leakage.
- Local MMD alignment between real and synthetic embeddings plus a Lipschitz regularizer on hypernetwork outputs mitigate non‑IID drift and stabilize training.
- A neutral “meta‑code” allows the trained system to synthesize domain‑agnostic samples, while mixtures of meta‑codes produce controllable multi‑domain data.
Abstract
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
Full Analysis
# Hypernetwork‑Driven Private Conditional VAEs for Federated Synthesis
**Authors:** Sunny Gupta, Amit Sethi
**Source:** [HuggingFace](None) | [arXiv](https://arxiv.org/abs/2601.00785)
**Published:** 2026-01-02
## Summary
- A shared hypernetwork generates client‑specific VAE decoders and class‑conditional latent priors from lightweight private codes, enabling personalization without exposing raw data.
- Differential‑privacy is enforced at the hypernetwork level by clipping and adding Gaussian noise to aggregated gradients, protecting against gradient‑based leakage.
- Local MMD alignment between real and synthetic embeddings plus a Lipschitz regularizer on hypernetwork outputs mitigate non‑IID drift and stabilize training.
- A neutral “meta‑code” allows the trained system to synthesize domain‑agnostic samples, while mixtures of meta‑codes produce controllable multi‑domain data.
## Abstract
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
---
*Topics: ai-ml, ai-safety*
*Difficulty: advanced*
*Upvotes: 0*