Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching

2025-01-20

AI Summary

To address video stalling caused by network fluctuations and high concurrency in wireless VR scenarios, this paper proposes a Field-of-View (FoV)-aware decentralized personalized federated learning (DP-FL) edge caching framework. Methodologically: (i) a DP-FL mechanism is designed to enable base station-level personalized cache policy optimization with PAC-learnable guarantees on cache hit rate; (ii) an Orthogonalized Binary Stochastic Gradient Descent (OBSGD) quantization scheme is introduced to reduce communication overhead via single-bit gradient compression while preserving convergence; and (iii) multicast/unicast packet scheduling is dynamically optimized based on real-time channel state information and FoV prediction. Evaluated on a real-world VR head-motion dataset, the framework achieves a 32% reduction in average latency and a 27% improvement in cache hit rate over LRU, LFU, and non-personalized FL baselines—demonstrating superior real-time performance, robustness against network dynamics, and strong privacy preservation.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of $mathcal{O}(1/sqrt{T})$ is obtained for the proposed algorithm, where $T$ is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms.

Problem

• Wireless Network
• Video Streaming
• Virtual Reality (VR) Experience

Innovation

• Field-aware Caching
• Decentralized Personalized Federated Learning (DP-FL)
• One-bit Quantized Stochastic Gradient Descent (OBSGD)