Loosely Coupled Federated Learning Over Generative Models

09/28/2020
by   Shaoming Song, et al.
0

Federated learning (FL) was proposed to achieve collaborative machine learning among various clients without uploading private data. However, due to model aggregation strategies, existing frameworks require strict model homogeneity, limiting the application in more complicated scenarios. Besides, the communication cost of FL's model and gradient transmission is extremely high. This paper proposes Loosely Coupled Federated Learning (LC-FL), a framework using generative models as transmission media to achieve low communication cost and heterogeneous federated learning. LC-FL can be applied on scenarios where clients possess different kinds of machine learning models. Experiments on real-world datasets covering different multiparty scenarios demonstrate the effectiveness of our proposal.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

03/28/2020

Semi-Federated Learning

Federated learning (FL) enables massive distributed Information and Comm...
01/28/2021

Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization

Federated learning (FL), as a type of distributed machine learning frame...
10/08/2021

FSL: Federated Supermask Learning

Federated learning (FL) allows multiple clients with (private) data to c...
04/29/2021

End-to-End Speech Recognition from Federated Acoustic Models

Training Automatic Speech Recognition (ASR) models under federated learn...
03/28/2022

Federated Learning with Position-Aware Neurons

Federated Learning (FL) fuses collaborative models from local nodes with...
04/15/2021

Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent

By leveraging deep learning based technologies, the data-driven based ap...
04/29/2022

Exploration and Exploitation in Federated Learning to Exclude Clients with Poisoned Data

Federated Learning (FL) is one of the hot research topics, and it utiliz...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.