mlsanityData to 14 Oct 2026

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

arXiv 2603.01363 ↗First posted 2 Mar 2026cs.LG cs.DCcited by 0

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 14 of its 23 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

14 of 23 references.

References · 14

  1. 2017Graph Attention Networkscited by 8,923
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  6. 2021Towards Personalized Federated Learningcited by 464
  7. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  8. 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
  9. 2022Personalized Federated Learning With Graphcited by 29
  10. 2023Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaborationcited by 23
  11. 2024Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decompositioncited by 15
  12. 2023A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand predictioncited by 9
2 more
  1. 2024Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattackscited by 4
  2. 2025Personalized Federated Learning via Learning Dynamic Graphscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Personalized Federated Sparse Adaptation of Time-Series Foundation Models
  2. 2024FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts
  3. 2026FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
  4. 2026QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
  5. 2024Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
  6. 2024pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning
  7. 2023Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings
  8. 2024FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation