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

翻译：联邦数据共享承诺在不集中原始数据的前提下实现效用，然而现有的嵌入级生成器在非独立同分布的客户端异构性下表现不佳，且针对梯度泄漏提供的正式保护有限。我们提出了FedHypeVAE，一种差分隐私、超网络驱动的框架，用于在去中心化客户端间合成嵌入级数据。该框架基于条件VAE主干，将单一的全局解码器和固定的先验分布替换为由共享超网络根据私有、可训练的客户端代码生成的客户端感知解码器和类条件先验分布。这种双层设计在生成层（而非下游模型）实现个性化，同时将本地数据与通信参数解耦。共享超网络在差分隐私约束下进行优化，确保仅聚合经过噪声扰动和裁剪的客户端梯度。真实嵌入与合成嵌入之间的局部最大均值差异对齐，以及对超网络输出的Lipschitz正则化，进一步增强了在非独立同分布条件下的稳定性和分布一致性。训练完成后，一个中性元代码支持领域无关的合成，而元代码的混合则提供了可控的多领域覆盖。FedHypeVAE在生成器层面统一了个性化、隐私保护和分布对齐，为联邦设置下的隐私保护数据合成奠定了理论基础。代码：github.com/sunnyinAI/FedHypeVAE