Graph Federated Learning with Hidden Representation Sharing

12/23/2022
by   Shuang Wu, et al.
2

Learning on Graphs (LoG) is widely used in multi-client systems when each client has insufficient local data, and multiple clients have to share their raw data to learn a model of good quality. One scenario is to recommend items to clients with limited historical data and sharing similar preferences with other clients in a social network. On the other hand, due to the increasing demands for the protection of clients' data privacy, Federated Learning (FL) has been widely adopted: FL requires models to be trained in a multi-client system and restricts sharing of raw data among clients. The underlying potential data-sharing conflict between LoG and FL is under-explored and how to benefit from both sides is a promising problem. In this work, we first formulate the Graph Federated Learning (GFL) problem that unifies LoG and FL in multi-client systems and then propose sharing hidden representation instead of the raw data of neighbors to protect data privacy as a solution. To overcome the biased gradient problem in GFL, we provide a gradient estimation method and its convergence analysis under the non-convex objective. In experiments, we evaluate our method in classification tasks on graphs. Our experiment shows a good match between our theory and the practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/16/2023

Federated Learning as a Network Effects Game

Federated Learning (FL) aims to foster collaboration among a population ...
research
01/20/2022

Federated Learning with Heterogeneous Architectures using Graph HyperNetworks

Standard Federated Learning (FL) techniques are limited to clients with ...
research
02/04/2023

FedSpectral+: Spectral Clustering using Federated Learning

Clustering in graphs has been a well-known research problem, particularl...
research
12/12/2021

Efficient and Reliable Overlay Networks for Decentralized Federated Learning

We propose near-optimal overlay networks based on d-regular expander gra...
research
06/08/2022

Gradient Obfuscation Gives a False Sense of Security in Federated Learning

Federated learning has been proposed as a privacy-preserving machine lea...
research
02/12/2020

Federated Clustering via Matrix Factorization Models: From Model Averaging to Gradient Sharing

Recently, federated learning (FL) has drawn significant attention due to...
research
05/03/2022

MS Lesion Segmentation: Revisiting Weighting Mechanisms for Federated Learning

Federated learning (FL) has been widely employed for medical image analy...

Please sign up or login with your details

Forgot password? Click here to reset