Federated Variational

Federated variational methods combine the principles of federated learning (training models on decentralized data) with variational inference (approximating complex probability distributions). The primary objective is to enable collaborative model training while preserving data privacy and addressing data heterogeneity across different sources. Current research focuses on adapting variational autoencoders (VAEs) and other generative models for federated settings, often incorporating techniques like gradient compression and disentangled representations to improve efficiency and personalization. This approach holds significant promise for applications requiring privacy-preserving machine learning across diverse datasets, such as in healthcare, industrial IoT, and personalized services based on sensitive user data.

Papers

July 12, 2024

FedVAE: Trajectory privacy preserving based on Federated Variational AutoEncoder
Yuchen Jiang, Ying Wu, Shiyao Zhang, James J. Q. Yu
Trajectory Data Trajectory Datasets Federated Variational Privacy Preserving Trajectory

May 22, 2024

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
Huiwen Wu, Xiaohan Li, Deyi Zhang, Xiaogang Xu, Jiafei Wu, Puning Zhao, Zhe Liu
Gradient Compression Centralized Learning Federated Variational Federated Tuning CG FedLLM

June 6, 2023

Personalization Disentanglement for Federated Learning: An explainable perspective
Peng Yan, Guodong Long
Latent Representation Synthesized View Model Personalization Dual Domain Anti Personalization Federated Variational

May 23, 2023

Federated Variational Inference: Towards Improved Personalization and Generalization
Elahe Vedadi, Joshua V. Dillon, Philip Andrew Mansfield, Karan Singhal, Arash Afkanpour, Warren Richard Morningstar
Strong Generalization Generative Modeling Variational Inference Generalization Bound Personalization Performance Hierarchical Generative Federated Variational

March 20, 2023

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder
Nan Yang, Xuanyu Chen, Charles Z. Liu, Dong Yuan, Wei Bao, Lizhen Cui
Semi Supervised Masked Autoencoders Federated Self Supervised Learning Pre Trained Classifier Federated Variational

February 7, 2023

Federated Variational Inference Methods for Structured Latent Variable Models
Conor Hassan, Robert Salomone, Kerrie Mengersen
Federated Learning Latent Structure FedAvg Algorithm Federated Variational Structured Variational

November 21, 2022

DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder
Bjarne Pfitzner, Bert Arnrich
Differential Privacy Variational Autoencoder Synthetic Data Generation Federated Variational

November 14, 2022

Federated Learning for Autoencoder-based Condition Monitoring in the Industrial Internet of Things
Soeren Becker, Kevin Styp-Rekowski, Oliver Vincent Leon Stoll, Odej Kao
Sensor Data Good Thing Based Anomaly Detection Predictive Maintenance Industrial Internet Vibration Data Federated Variational

Federated Variational

Papers

FedVAE: Trajectory privacy preserving based on Federated Variational AutoEncoder

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

Personalization Disentanglement for Federated Learning: An explainable perspective

Federated Variational Inference: Towards Improved Personalization and Generalization

FedMAE: Federated Self-Supervised Learning with One-Block Masked Auto-Encoder

Federated Variational Inference Methods for Structured Latent Variable Models

DPD-fVAE: Synthetic Data Generation Using Federated Variational Autoencoders With Differentially-Private Decoder

Federated Learning for Autoencoder-based Condition Monitoring in the Industrial Internet of Things