Digital Ethics in Federated Learning

TL;DR

This paper examines digital ethics issues in federated learning for IoT, focusing on fairness, incentives, and continuity challenges, and discusses solutions and future opportunities for human-centric applications.

Contribution

It provides a comprehensive analysis of ethical challenges in federated learning for IoT and explores solutions from both client and server perspectives, including centralized and decentralized models.

Findings

Identifies key ethical challenges like fairness and incentives in FL.

Analyzes solutions from client and server viewpoints.

Suggests future directions for human-centric IoT applications.

Abstract

The Internet of Things (IoT) consistently generates vast amounts of data, sparking increasing concern over the protection of data privacy and the limitation of data misuse. Federated learning (FL) facilitates collaborative capabilities among multiple parties by sharing machine learning (ML) model parameters instead of raw user data, and it has recently gained significant attention for its potential in privacy preservation and learning efficiency enhancement. In this paper, we highlight the digital ethics concerns that arise when human-centric devices serve as clients in FL. More specifically, challenges of game dynamics, fairness, incentive, and continuity arise in FL due to differences in perspectives and objectives between clients and the server. We analyze these challenges and their solutions from the perspectives of both the client and the server, and through the viewpoints of centralized and decentralized FL. Finally, we explore the opportunities in FL for human-centric IoT as directions for future development.