Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing
On the map: Mixture-of-experts → Federated mixture-of-experts
Abstract (arXiv)
Recent advancements in large artificial intelligence models (LAMs) are driving significant innovations in mobile edge computing within next-generation wireless networks. However, the substantial demands for computational resources and larges-cale training data required to train LAMs conflict with the limited storage and computational capacity of edge devices, posing significant challenges to training and deploying LAMs at the edge. In this work, we introduce the Networked Mixture-of-Experts (NMoE) system, in which clients perform inference collaboratively by distributing tasks to suitable neighbors based on their expertise and aggregate the returned results. For training the NMoE, we propose a federated learning framework that integrates both supervised and self-supervised learning to balance personalization and generalization, while preserving communication efficiency and data privacy. We conduct extensive experiments to demonstrate the efficacy of the proposed NMoE system, providing insights for the NMoE training algorithms.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Federated mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 15 of its 20 references that are in the map. First posted on arXiv 3 Nov 2025.
Builds on
15 of 20 references.
Closest ancestors · 4
Same direction, newest first
- 2025Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach8 Jul
- 2024FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts21 Aug
- 2024pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning2 Feb
- 2020PFL-MoE: Personalized Federated Learning Based on Mixture of Experts31 Dec
Other references · 11
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
- 2025Muon is Scalable for LLM Trainingcited by 381
- 2021Federated Learning on Non-IID Data: A Surveycited by 345
- 2016Resnet in Resnet: Generalizing Residual Architecturescited by 110
- 2022HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training Systemcited by 36
- 2023Big AI Models for 6G Wireless Networks: Opportunities, Challenges, and Research Directionscited by 32
- 2024FedSC: Provable Federated Self-supervised Learning with Spectral Contrastive Objective over Non-i.i.d. Datacited by 5
- 2025Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Functioncited by 5
- 2025Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edgecited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025FLEX-MoE: Federated Mixture-of-Experts with Load-balanced Expert Assignment for Edge Computing
- 2024Theory of Mixture-of-Experts for Mobile Edge Computing
- 2026HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts
- 2025Edge-Assisted Collaborative Fine-Tuning for Multi-User Personalized Artificial Intelligence Generated Content (AIGC)
- 2025CoMoE: Collaborative Optimization of Expert Aggregation and Offloading for MoE-based LLMs at Edge
- 2023Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
- 2024FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation
- 2026FedCoE: Bridging Generalization and Personalization via Federated Coordinated Dual-level MoEs