This repository explores federated deep generative models with PyTorch, featuring Conditional DCGAN, FedGAN v2, and custom synchronization strategies. It demonstrates client-server training with FedAvg, non-IID data splits, and GAN evaluation, providing a foundation for research in privacy-preserving generative modeling.
transformers pytorch differential-privacy edge-computing distributed-training federated-learning deep-generative-models federated-optimization privacy-preserving-ml diffusion-models secure-aggregation federated-gan non-iid-data federated-vae ml-reproducibility
-
Updated
Oct 14, 2025 - Jupyter Notebook