Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting
This addresses the challenge of personalized federated learning for time-series forecasting in distributed settings like electric vehicle charging, representing an incremental improvement over existing methods.
The paper tackles the problem of client heterogeneity in federated learning for time-series forecasting by proposing Fed-GAME, which uses a learnable dynamic implicit graph and a Graph Attention Mixture-of-Experts aggregator for personalization, resulting in outperformance over state-of-the-art personalized FL baselines on two real-world electric vehicle charging datasets.
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.