用超网络生成个性化嵌入，实现联邦学习中隐私保护的数据合成。
FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
- 通过超网络动态生成客户端专属解码器和类别条件先验
- 在非独立同分布下仍保持嵌入分布一致性，且满足差分隐私
- 适合需要隐私保护与跨域数据共享的医疗、金融等场景
联邦数据共享可在不集中原始数据的前提下实现价值，但现有嵌入级生成方法在客户端异构性下表现不佳，且对梯度泄露缺乏严格保护。我们提出 FedHypeVAE，一种基于差分隐私与超网络驱动的嵌入级数据合成框架。在条件变分自编码器基础上，用共享超网络生成客户端感知的解码器与类别条件先验，取代单一全局解码器与固定先验。该双层设计使生成层个性化而非下游模型，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优化，仅聚合加噪剪裁后的梯度。本地 MMD 对齐与超网络输出的 Lipschitz 正则化进一步提升非独立同分布条件下的稳定性与分布一致性。训练后，中性元码可实现无域偏移合成，多元码混合则支持可控的多域覆盖。FedHypeVAE 在生成器层面统一了个性化、隐私与分布对齐，为联邦环境下的隐私保护数据合成提供了原则性基础。代码：github.com/sunnyinAI/FedHypeVAE
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。