Robust Federated Learning by Mixture of Experts
On the map: Mixture-of-experts → Federated mixture-of-experts
Abstract (arXiv)
We present a novel weighted average model based on the mixture of experts (MoE) concept to provide robustness in Federated learning (FL) against the poisoned/corrupted/outdated local models. These threats along with the non-IID nature of data sets can considerably diminish the accuracy of the FL model. Our proposed MoE-FL setup relies on the trust between users and the server where the users share a portion of their public data sets with the server. The server applies a robust aggregation method by solving the optimization problem or the Softmax method to highlight the outlier cases and to reduce their adverse effect on the FL process. Our experiments illustrate that MoE-FL outperforms the performance of the traditional aggregation approach for high rate of poisoned data from attackers.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Federated mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 12 of its 20 references that are in the map. First posted on arXiv 23 Apr 2021.
Builds on
12 of 20 references.
References · 12
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
- 2018How To Backdoor Federated Learningcited by 745
- 2019Federated Machine Learning: Concept and Applicationscited by 409
- 2019Fair Resource Allocation in Federated Learningcited by 389
- 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 361
- 2019Robust Aggregation for Federated Learningcited by 314
- 2019Can You Really Backdoor Federated Learning?cited by 250
- 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
- 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
- 2018A generic framework for privacy preserving deep learningcited by 103
- 2020A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimizationcited by 3
Built on by
Citing papers per year: 2024: 3; 2025: 1.
4 papers.
- 2024A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learningcited by 52
- 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
- 2024Towards Vision Mixture of Experts for Wildlife Monitoring on the Edgecited by 2
- 2025Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learningcited by 0
- 2025Shift Happens: Mixture of Experts based Continual Adaptation in Federated Learning23 Jun 2025
- 2024Towards Vision Mixture of Experts for Wildlife Monitoring on the Edge12 Nov 2024
- 2024A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning13 Aug 2024
- 2024Advances and Open Challenges in Federated Foundation Models23 Apr 2024
Similar, not cited
Close in wording, no citation either way
- 2025Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach
- 2024FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation
- 2021Personalised Federated Learning: A Combinational Approach
- 2025Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach
- 2020Specialized federated learning using a mixture of experts
- 2022On the Adversarial Robustness of Mixture of Experts
- 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts
- 2025PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning