FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation
Not on the map. Why?
Abstract (arXiv)
Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite its advantages, practical FEL deployment faces significant challenges related to device constraints and device-server interactions, necessitating heterogeneous, user-adaptive model training with limited and uncertain communication. In this paper, we introduce FedCache 2.0, a novel personalized FEL architecture that simultaneously addresses these challenges. FedCache 2.0 incorporates the benefits of both dataset distillation and knowledge cache-driven federated learning by storing and organizing distilled data as knowledge in the server-side knowledge cache. Moreover, a device-centric cache sampling strategy is introduced to tailor transferred knowledge for individual devices within controlled communication bandwidth. Extensive experiments on five datasets covering image recognition, audio understanding, and mobile sensor data mining tasks demonstrate that (1) FedCache 2.0 significantly outperforms state-of-the-art methods regardless of model structures, data distributions, and modalities. (2) FedCache 2.0 can train splendid personalized on-device models with at least ×28.6 improvement in communication efficiency.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 57 references that are in the map. First posted on arXiv 22 May 2024.
Builds on
33 of 57 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2020Adaptive Federated Optimizationcited by 1,036
- 2021Towards Personalized Federated Learningcited by 462
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
- 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
- 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
- 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 185
- 2021Federated Learning for Smart Healthcare: A Surveycited by 182
21 more
- 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
- 2023A Comprehensive Survey of Dataset Distillationcited by 114
- 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
- 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
- 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
- 2021Personalized Federated Learning through Local Memorizationcited by 57
- 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
- 2020Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computingcited by 52
- 2021Federated Learning for Internet of Things: Applications, Challenges, and Opportunitiescited by 49
- 2022Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environmentscited by 49
- 2022Federated Unlearning for On-Device Recommendationcited by 39
- 2023Towards Personalized Federated Learning via Heterogeneous Model Reassemblycited by 31
- 2020Federated Edge Learning : Design Issues and Challengescited by 26
- 2022Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillationcited by 22
- 2023FedICT: Federated Multi-task Distillation for Multi-access Edge Computingcited by 17
- 2023FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligencecited by 17
- 2021Edge-Native Intelligence for 6G Communications Driven by Federated Learning: A Survey of Trends and Challengescited by 12
- 2023Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaborationcited by 10
- 2023PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learningcited by 8
- 2024Spectral Co-Distillation for Personalized Federated Learningcited by 8
- 2024Federated Class-Incremental Learning with New-Class Augmented Self-Distillationcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.