Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gupta, Sunny, Sethi, Amit
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.00785
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917180534161408
author Gupta, Sunny
Sethi, Amit
author_facet Gupta, Sunny
Sethi, Amit
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2601_00785
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
Gupta, Sunny
Sethi, Amit
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
I.2.6; I.5.1; I.4; C.2.4; E.3
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
title FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
I.2.6; I.5.1; I.4; C.2.4; E.3
url https://arxiv.org/abs/2601.00785