F2STNet联合频谱与状态空间建模，实现高效公平的图数据预测。
F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting
- 融合图傅里叶特征与轻量状态空间编码器，捕捉图结构与长时依赖。
- 在PeMS04等数据集上优于基线模型，最差客户端误差降低12.3%。
- 引入公平联邦聚合机制，适合数据异构场景下的分布式预测任务。
图结构数据的时空预测对交通预测和环境监测至关重要，但分散且异构的数据使序列建模与协同训练面临挑战。我们提出F²STNet，一种结合截断图傅里叶特征、轻量级对角状态空间时间编码器、图卷积及公平性感知联邦聚合（FFA）的联邦预测框架。频谱分支揭示图频域结构，状态空间层以序列长度线性复杂度建模长时依赖。FFA通过客户端验证损失与递增公平调度调整FedAvg先验。在PeMS04、HZMetro和KnowAir上的实验表明，其预测精度优于对比基线；在PeMS04的联邦实验中，最差客户端性能与客户端差异指标均有提升。
原文摘要 · Abstract (English)
Spatiotemporal prediction on graph-structured data is central to traffic forecasting and environmental monitoring, yet decentralized and heterogeneous data complicate both sequence modeling and collaborative training. We propose F$^2$STNet, 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). The spectral branch exposes graph-frequency structure, while the state-space layer models long temporal dependencies with linear complexity in the sequence length. FFA adjusts the FedAvg prior using client validation losses and an increasing fairness schedule. Experiments on PeMS04, HZMetro, and KnowAir show favorable forecasting accuracy relative to the evaluated baselines; federated experiments on PeMS04 additionally improve worst-client and client-dispersion metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。