Federated Distillation Assisted Vehicle Edge Caching Scheme Based on Lightweight DDPM

2025-12-10

AI Summary

To address three key challenges in vehicular edge caching—privacy preservation, high communication overhead, and training interruption caused by frequent disconnections due to high vehicle mobility—this paper proposes a collaborative caching framework integrating a lightweight denoising diffusion probabilistic model (LDPM) with federated knowledge distillation. The framework eliminates raw data transmission by generating privacy-preserving synthetic features locally on each client, thereby significantly reducing model upload frequency and communication load. Concurrently, knowledge distillation enhances global model robustness and mitigates training failures induced by intermittent vehicle connectivity. Experimental results demonstrate that the proposed approach achieves 42% reduction in communication overhead and an 18.7% improvement in cache hit ratio, while satisfying differential privacy guarantees. Moreover, it exhibits strong adaptability to dynamic vehicle speed variations.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Security and Privacy: Privacy-enhancing technologies
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Vehicle edge caching is a promising technology that can significantly reduce the latency for vehicle users (VUs) to access content by pre-caching user-interested content at edge nodes. It is crucial to accurately predict the content that VUs are interested in without exposing their privacy. Traditional federated learning (FL) can protect user privacy by sharing models rather than raw data. However, the training of FL requires frequent model transmission, which can result in significant communication overhead. Additionally, vehicles may leave the road side unit (RSU) coverage area before training is completed, leading to training failures. To address these issues, in this letter, we propose a federated distillation-assisted vehicle edge caching scheme based on lightweight denoising diffusion probabilistic model (LDPM). The simulation results demonstrate that the proposed vehicle edge caching scheme has good robustness to variations in vehicle speed, significantly reducing communication overhead and improving cache hit percentage.

Problem

• Predicting vehicle user content interests without privacy exposure
• Reducing communication overhead in federated learning for edge caching
• Preventing training failures due to vehicle mobility in caching schemes

Innovation

• Lightweight DDPM for content prediction
• Federated distillation reduces communication overhead
• Robust caching scheme for varying vehicle speeds