# FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence

arXiv: https://arxiv.org/abs/2308.07816 · HTML: https://mlsanity.com/paper/2308.07816/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2023.

## Built on by (most cited first, 17 of 17)

- [Federated Skewed Label Learning with Logits Fusion](https://mlsanity.com/paper/2311.08202/) (2023)
- [FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data](https://mlsanity.com/paper/2512.02350/) (2025)
- [Federated Class-Incremental Learning with New-Class Augmented Self-Distillation](https://mlsanity.com/paper/2401.00622/) (2024)
- [HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data](https://mlsanity.com/paper/2509.06444/) (2025)
- [Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment](https://mlsanity.com/paper/2508.08278/) (2025)
- [Logits Poisoning Attack in Federated Distillation](https://mlsanity.com/paper/2401.03685/) (2024)
- [Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates](https://mlsanity.com/paper/2312.04166/) (2023)
- [FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation](https://mlsanity.com/paper/2405.13378/) (2024)
- [Peak-Controlled Logits Poisoning Attack in Federated Distillation](https://mlsanity.com/paper/2407.18039/) (2024)
- [Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration](https://mlsanity.com/paper/2501.00693/) (2025)
- [Hierarchical Knowledge Structuring for Effective Federated Learning in Heterogeneous Environments](https://mlsanity.com/paper/2504.03505/) (2025)
- [Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation](https://mlsanity.com/paper/2504.19602/) (2025)
- [Privacy-Enhanced Training-as-a-Service for On-Device Intelligence: Concept, Architectural Scheme, and Open Problems](https://mlsanity.com/paper/2404.10255/) (2024)
- [Caching Techniques for Reducing the Communication Cost of Federated Learning in IoT Environments](https://mlsanity.com/paper/2507.17772/) (2025)
- [Personalized Federated Distillation Assisted Vehicle Edge Caching Strategy](https://mlsanity.com/paper/2512.09378/) (2025)
- [GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems](https://mlsanity.com/paper/2603.18540/) (2026)
- [FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling](https://mlsanity.com/paper/2604.16574/) (2026)

## Abstract (arXiv)

Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data sources. To protect data privacy and unify data silos among end devices in EI, Federated Learning (FL) is proposed for collaborative training of shared AI models across devices without compromising data privacy. However, the prevailing FL approaches cannot guarantee model generalization and adaptation on heterogeneous clients. Recently, Personalized Federated Learning (PFL) has drawn growing awareness in EI, as it enables a productive balance between local-specific training requirements inherent in devices and global-generalized optimization objectives for satisfactory performance. However, most existing PFL methods are based on the Parameters Interaction-based Architecture (PIA) represented by FedAvg, which causes unaffordable communication burdens due to large-scale parameters transmission between devices and the edge server. In contrast, Logits Interaction-based Architecture (LIA) allows to update model parameters with logits transfer and gains the advantages of communication lightweight and heterogeneous on-device model allowance compared to PIA. Nevertheless, previous LIA methods attempt to achieve satisfactory performance either relying on unrealistic public datasets or increasing communication overhead for additional information transmission other than logits. To tackle this dilemma, we propose a knowledge cache-driven PFL architecture, named FedCache, which reserves a knowledge cache on the server for fetching personalized knowledge from the samples with similar hashes to each given on-device sample. During the training phase, ensemble distillation is applied to on-device models for constructive optimization with personalized knowledge transferred from the server-side knowledge cache.