Decentralized Fairness Aware Multi Task Federated Learning for VR Network

TL;DR

This paper proposes a decentralized multi-task federated learning approach for VR network caching, personalizing content delivery to improve quality and reduce bias across users and base stations.

Contribution

It introduces a novel DMTFL algorithm that personalizes caching strategies in VR networks, with theoretical guarantees and improved performance over baselines.

Findings

DMTFL outperforms baseline algorithms in simulations.

Theoretical guarantees on model performance are established.

Personalized caching improves VR experience quality.

Abstract

Wireless connectivity promises to unshackle virtual reality (VR) experiences, allowing users to engage from anywhere, anytime. However, delivering seamless, high-quality, real-time VR video wirelessly is challenging due to the stringent quality of experience requirements, low latency constraints, and limited VR device capabilities. This paper addresses these challenges by introducing a novel decentralized multi task fair federated learning (DMTFL) based caching that caches and prefetches each VR user's field of view (FOV) at base stations (BSs) based on the caching strategies tailored to each BS. In federated learning (FL) in its naive form, often biases toward certain users, and a single global model fails to capture the statistical heterogeneity across users and BSs. In contrast, the proposed DMTFL algorithm personalizes content delivery by learning individual caching models at each BS. These models are further optimized to perform well under any target distribution, while providing theoretical guarantees via Rademacher complexity and a probably approximately correct (PAC) bound on the loss. Using a realistic VR head-tracking dataset, our simulations demonstrate the superiority of our proposed DMTFL algorithm compared to baseline algorithms.