Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908872812265472 |
|---|---|
| author | Gao, Song Zhang, Songyang Jing, Shusen Zhang, Shuai Zhou, Xiangwei Wang, Yue Cai, Zhipeng |
| author_facet | Gao, Song Zhang, Songyang Jing, Shusen Zhang, Shuai Zhou, Xiangwei Wang, Yue Cai, Zhipeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01743 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing Gao, Song Zhang, Songyang Jing, Shusen Zhang, Shuai Zhou, Xiangwei Wang, Yue Cai, Zhipeng Machine Learning Artificial Intelligence Networking and Internet Architecture 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. |
| title | Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing |
| topic | Machine Learning Artificial Intelligence Networking and Internet Architecture |
| url | https://arxiv.org/abs/2511.01743 |