A Systematic Review of Federated Generative Models

TL;DR

This paper systematically reviews the intersection of Federated Learning and Generative Models from 2019 to 2024, highlighting advancements, challenges, and future directions in privacy-preserving distributed data generation.

Contribution

It provides a comprehensive comparison of nearly 100 studies, summarizes key methods, and identifies unresolved challenges in federated generative modeling.

Findings

Significant progress in federated generative techniques

Identification of privacy and security challenges

Future research directions outlined

Abstract

Federated Learning (FL) has emerged as a solution for distributed systems that allow clients to train models on their data and only share models instead of local data. Generative Models are designed to learn the distribution of a dataset and generate new data samples that are similar to the original data. Many prior works have tried proposing Federated Generative Models. Using Federated Learning and Generative Models together can be susceptible to attacks, and designing the optimal architecture remains challenging. This survey covers the growing interest in the intersection of FL and Generative Models by comprehensively reviewing research conducted from 2019 to 2024. We systematically compare nearly 100 papers, focusing on their FL and Generative Model methods and privacy considerations. To make this field more accessible to newcomers, we highlight the state-of-the-art advancements and identify unresolved challenges, offering insights for future research in this evolving field.