Group privacy for personalized federated learning

06/07/2022
by   Filippo Galli, et al.
0

Federated learning is a type of collaborative machine learning, where participating clients process their data locally, sharing only updates to the collaborative model. This enables to build privacy-aware distributed machine learning models, among others. The goal is the optimization of a statistical model's parameters by minimizing a cost function of a collection of datasets which are stored locally by a set of clients. This process exposes the clients to two issues: leakage of private information and lack of personalization of the model. On the other hand, with the recent advancements in techniques to analyze data, there is a surge of concern for the privacy violation of the participating clients. To mitigate this, differential privacy and its variants serve as a standard for providing formal privacy guarantees. Often the clients represent very heterogeneous communities and hold data which are very diverse. Therefore, aligned with the recent focus of the FL community to build a framework of personalized models for the users representing their diversity, it is also of utmost importance to protect against potential threats against the sensitive and personal information of the clients. d-privacy, which is a generalization of geo-indistinguishability, the lately popularized paradigm of location privacy, uses a metric-based obfuscation technique that preserves the spatial distribution of the original data. To address the issue of protecting the privacy of the clients and allowing for personalized model training to enhance the fairness and utility of the system, we propose a method to provide group privacy guarantees exploiting some key properties of d-privacy which enables personalized models under the framework of FL. We provide with theoretical justifications to the applicability and experimental validation on real-world datasets to illustrate the working of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/01/2023

Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond

Federated learning (FL) is a framework for training machine learning mod...
research
04/15/2023

PI-FL: Personalized and Incentivized Federated Learning

Personalized FL has been widely used to cater to heterogeneity challenge...
research
11/25/2020

Advancements of federated learning towards privacy preservation: from federated learning to split learning

In the distributed collaborative machine learning (DCML) paradigm, feder...
research
11/03/2020

An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee

The issue of potential privacy leakage during centralized AI's model tra...
research
01/29/2019

Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System

The increasing interest in user privacy is leading to new privacy preser...
research
01/17/2023

Graph Topology Learning Under Privacy Constraints

Graph learning, which aims to infer the underlying topology behind high ...
research
01/12/2021

Personalized Federated Deep Learning for Pain Estimation From Face Images

Standard machine learning approaches require centralizing the users' dat...

Please sign up or login with your details

Forgot password? Click here to reset