Federated Generative

Federated generative models combine federated learning's privacy-preserving distributed training with the data generation capabilities of generative models. Current research emphasizes efficient algorithms, such as those employing one-shot learning or on-demand quantization, to reduce communication overhead and energy consumption, particularly for resource-constrained devices like those in the Internet of Things. This approach addresses the challenges of training generative models on decentralized, heterogeneous data while maintaining data privacy, with applications ranging from robotics and drug discovery to personalized travel time estimation. The resulting models offer improved efficiency and robustness compared to traditional centralized methods.

Papers

May 26, 2024

A Systematic Review of Federated Generative Models
Ashkan Vedadi Gargary, Emiliano De Cristofaro
Generative Model Systematic Review Generative Modelling Model Sharing Federated Generative

April 30, 2024

Harnessing Federated Generative Learning for Green and Sustainable Internet of Things
Yuanhang Qi, M. Shamim Hossain
Federated Learning Internet of Thing Internet of Thing Device Good Thing One Shot Federated Learning Federated Generative Network Energy Efficiency

March 16, 2024

Feature Aggregation with Latent Generative Replay for Federated Continual Learning of Socially Appropriate Robot Behaviours
Nikhil Churamani, Saksham Checker, Hao-Tien Lewis Chiang, Hatice Gunes
Social Robot Feature Aggregation Generative Replay Federated Continual Learning Weight Aggregation Federated Generative

March 7, 2024

On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks
Bingkun Lai, Jiayi He, Jiawen Kang, Gaolei Li, Minrui Xu, Tao zhang, Shengli Xie
Generative Artificial Intelligence Generative Diffusion Model Diffusion Training Dynamic Quantization Federated Generative

June 28, 2023

Federated Generative Learning with Foundation Models
Jie Zhang, Xiaohua Qi, Bo Zhao
Generative Model Foundation Model Learning Framework FedAvg Converges Federated Generative

June 7, 2023

Phoenix: A Federated Generative Diffusion Model
Fiona Victoria Stanley Jothiraj, Afra Mashhadi
Generative Model Generative Adversarial Network Federated Generative

June 3, 2023

GPT-FL: Generative Pre-trained Model-Assisted Federated Learning
Tuo Zhang, Tiantian Feng, Samiul Alam, Dimitrios Dimitriadis, Sunwoo Lee, Mi Zhang, Shrikanth S. Narayanan, Salman Avestimehr
Synthetic Data Federated Learning Generative Question Pre Trained Generative Model Federated Generative

April 11, 2023

GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery
Daniel Manu, Jingjing Yao, Wuji Liu, Xiang Sun
Generative Adversarial Network GAN Model Known Molecule Drug Discovery Process Federated Generative

January 30, 2023

FedFA: Federated Feature Augmentation
Tianfei Zhou, Ender Konukoglu
Latent Feature Statistical Feature Federated Generative

July 2, 2022

GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation
Zhiwen Zhang, Hongjun Wang, Jiyuan Chen, Zipei Fan, Xuan Song, Ryosuke Shibasaki
Trajectory Data Travel Time Estimation Real Time Traffic Federated Generative Real World Taxi

Federated Generative

Papers

A Systematic Review of Federated Generative Models

Harnessing Federated Generative Learning for Green and Sustainable Internet of Things

Feature Aggregation with Latent Generative Replay for Federated Continual Learning of Socially Appropriate Robot Behaviours

On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks

Federated Generative Learning with Foundation Models

Phoenix: A Federated Generative Diffusion Model

GPT-FL: Generative Pre-trained Model-Assisted Federated Learning

GraphGANFed: A Federated Generative Framework for Graph-Structured Molecules Towards Efficient Drug Discovery

FedFA: Federated Feature Augmentation

GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation