Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting

2026-03-01

AI Summary

This work addresses the challenge in federated learning that static graph structures struggle to accommodate client heterogeneity and enable personalized time series forecasting. To this end, the authors propose a fine-grained personalization approach based on a learnable dynamic implicit graph. By decomposing client-specific parameter deviations into consensus updates and personalized aggregations, and incorporating a Graph Attention Mixture of Experts (GAME) mechanism, the method adaptively models evolving topological relationships among clients. This approach overcomes the limitations of conventional static graphs and achieves significantly superior performance compared to existing personalized federated learning methods on two real-world electric vehicle charging datasets, thereby enhancing the accuracy of time series predictions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Game Theory and Economic Paradigms: Adversarial Learning
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Federated learning (FL) on graphs shows promise for distributed time-series forecasting. Yet, existing methods rely on static topologies and struggle with client heterogeneity. We propose Fed-GAME, a framework that models personalized aggregation as message passing over a learnable dynamic implicit graph. The core is a decoupled parameter difference-based update protocol, where clients transmit parameter differences between their fine-tuned private model and a shared global model. On the server, these differences are decomposed into two streams: (1) averaged difference used to updating the global model for consensus (2) the selective difference fed into a novel Graph Attention Mixture-of-Experts (GAME) aggregator for fine-grained personalization. In this aggregator, shared experts provide scoring signals while personalized gates adaptively weight selective updates to support personalized aggregation. Experiments on two real-world electric vehicle charging datasets demonstrate that Fed-GAME outperforms state-of-the-art personalized FL baselines.

Problem

• federated learning
• client heterogeneity
• time-series forecasting
• graph topology
• personalization

Innovation

• Federated Learning
• Graph Attention
• Mixture-of-Experts
• Personalized Aggregation
• Time-Series Forecasting