Preprint
Aug 2026
F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting
F$^2$STNet is proposed, a federated forecasting framework that combines truncated graph-Fourier features, a lightweight diagonal state-space temporal encoder, graph convolution, and Fairness-aware Federated Aggregation (FFA).
Jiayi Zhang, Jinfeng Xu, Hewei Wang et al.
· 0 citations