FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911760120807424 |
|---|---|
| author | Yan, Biwei Zhang, Hongliang Xu, Minghui Yu, Dongxiao Cheng, Xiuzhen |
| author_facet | Yan, Biwei Zhang, Hongliang Xu, Minghui Yu, Dongxiao Cheng, Xiuzhen |
| contents | Federated learning is a powerful technique that enables collaborative learning among different clients. Prototype-based federated learning is a specific approach that improves the performance of local models under non-IID (non-Independently and Identically Distributed) settings by integrating class prototypes. However, prototype-based federated learning faces several challenges, such as prototype redundancy and prototype failure, which limit its accuracy. It is also susceptible to poisoning attacks and server malfunctions, which can degrade the prototype quality. To address these issues, we propose FedRFQ, a prototype-based federated learning approach that aims to reduce redundancy, minimize failures, and improve \underline{q}uality. FedRFQ leverages a SoftPool mechanism, which effectively mitigates prototype redundancy and prototype failure on non-IID data. Furthermore, we introduce the BFT-detect, a BFT (Byzantine Fault Tolerance) detectable aggregation algorithm, to ensure the security of FedRFQ against poisoning attacks and server malfunctions. Finally, we conduct experiments on three different datasets, namely MNIST, FEMNIST, and CIFAR-10, and the results demonstrate that FedRFQ outperforms existing baselines in terms of accuracy when handling non-IID data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07558 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality Yan, Biwei Zhang, Hongliang Xu, Minghui Yu, Dongxiao Cheng, Xiuzhen Distributed, Parallel, and Cluster Computing Machine Learning Federated learning is a powerful technique that enables collaborative learning among different clients. Prototype-based federated learning is a specific approach that improves the performance of local models under non-IID (non-Independently and Identically Distributed) settings by integrating class prototypes. However, prototype-based federated learning faces several challenges, such as prototype redundancy and prototype failure, which limit its accuracy. It is also susceptible to poisoning attacks and server malfunctions, which can degrade the prototype quality. To address these issues, we propose FedRFQ, a prototype-based federated learning approach that aims to reduce redundancy, minimize failures, and improve \underline{q}uality. FedRFQ leverages a SoftPool mechanism, which effectively mitigates prototype redundancy and prototype failure on non-IID data. Furthermore, we introduce the BFT-detect, a BFT (Byzantine Fault Tolerance) detectable aggregation algorithm, to ensure the security of FedRFQ against poisoning attacks and server malfunctions. Finally, we conduct experiments on three different datasets, namely MNIST, FEMNIST, and CIFAR-10, and the results demonstrate that FedRFQ outperforms existing baselines in terms of accuracy when handling non-IID data. |
| title | FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Quality |
| topic | Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2401.07558 |