Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing
This addresses the problem of deploying large AI models in mobile edge computing for edge devices, but it appears incremental as it builds on existing federated learning and mixture-of-experts concepts.
The paper tackles the challenge of training large AI models on resource-constrained edge devices by introducing a Networked Mixture-of-Experts system that enables collaborative inference and a federated learning framework for training, demonstrating efficacy through extensive experiments.
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 large-scale 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 infer 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 and benchmarks for the NMoE training algorithms.