Federated Learning Assisted Edge Caching Scheme Based on Lightweight Architecture DDPM
Edge caching is an emerging technology that empowers caching units at edge nodes, allowing users to fetch contents of interest that have been pre-cached at the edge nodes. The key to pre-caching is to maximize the cache hit percentage for cached content without compromising users’ privacy. In this letter, we propose a federated learning (FL) assisted edge caching scheme based on lightweight architecture denoising diffusion probabilistic model (LDPM). Our simulation results verify that our proposed scheme achieves a higher cache hit percentage compared to existing FL-based methods and baseline methods.
Authors
- Kezhi Wang (ORCID: https://orcid.org/0000-0001-8602-0800)
- Qiong Wu (ORCID: https://orcid.org/0000-0002-4899-1718)
- Nan Cheng (ORCID: https://orcid.org/0000-0001-7907-2071)
- Khaled B. Letaief (ORCID: https://orcid.org/0000-0003-2519-6401)
- Pingyi Fan (ORCID: https://orcid.org/0000-0002-0658-6079)
- Xun Li (ORCID: https://orcid.org/0000-0002-1267-9263)
Institutions
- Jiangnan University (CN)
- Xidian University (CN)
- Hong Kong University of Science and Technology (HK)
- Xi’an University of Posts and Telecommunications (CN)
- Brunel University of London (GB)
- Middlesex University London (GB)
- University of Hong Kong (HK)
- Tsinghua University (CN)
Publication Details
- Journal
- IEEE Networking Letters
- Published
- 2025-08-18
- DOI
- https://doi.org/10.1109/lnet.2025.3599196
- Citations
- 1
- Primary Topic
- Caching and Content Delivery
- Type
- article
- Field-Weighted Citation Impact
- 1.49
Funders
- National Natural Science Foundation of China