TL;DR
FedTP is proposed, a federated learning framework that integrates gradient conflict elimination into the aggregation process and harmonizes local updates, thereby improving fairness across clients without compromising overall predictive accuracy.
The rapid growth of Intelligent Transportation Systems (ITSs) and Internet of Things (IoT) technologies has generated massive volumes of distributed traffic data, creating significant challenges related to privacy, scalability, communication overhead, and heterogeneous traffic patterns. To address these challenges, this paper proposes FedTraffic, a hierarchical federated learning framework for traffic flow forecasting that integrates Edge–Fog–Cloud computing, hybrid deep learning, adaptive federated optimization, and Explainable Artificial Intelligence (XAI). The proposed framework combines a Temporal Convolutional Network–Conditional Variational Autoencoder (TCN–CVAE) with traffic-behavior clustering, adaptive client selection, and hierarchical model aggregation to enable accurate, privacy-preserving, and interpretable traffic prediction under heterogeneous non-IID environments. Extensive experiments demonstrate that FedTraffic achieves a best Mean Absolute Error (MAE) of 2.12, a Root Mean Square Error (RMSE) of 4.28, a Mean Absolute Percentage Error (MAPE) of 5.47%, and an R2 score of 0.966. Compared with the strongest federated baseline, it improves MAE by up to 18.77%, RMSE by 16.41%, and MAPE by more than 22%, while reducing communication overhead through an 8:1 latent representation compression ratio. These results demonstrate the effectiveness of FedTraffic as a scalable, privacy-preserving, and interpretable solution for next-generation intelligent transportation systems.
Experiments on controlled synthetic data and the Q-Traffic real-world dataset demonstrate that the proposed framework improves predictive accuracy, cross-client stability, and robustness under heterogeneous federated traffic scenarios.
Federated Learning (FL) enables collaborative model training without sharing raw data, but its effectiveness degrades under Non-IID client data and inefficient participation. In such settings, FedAvg may exhibit slow convergence, high variance across rounds, and elevated communication overhead. We propose a clustered ensemble framework to improve training stability and communication efficiency under label-skewed Non-IID distributions. Clients are clustered by data similarity, and one model is trained per cluster. At inference time, we employ a confidence-based ensemble that selects (or combines) cluster models, while adaptive client selection regulates participation within clusters to reduce redundant communication. Experiments on MNIST, Fashion-MNIST, CIFAR-10, and SVHN show more stable learning dynamics and lower communication cost while maintaining competitive accuracy compared to FedAvg. We also analyze how participation policies affect convergence behavior and client fairness.
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.
Federated learning (FL) enables cellular traffic prediction without centralizing raw base-station data, but statistical heterogeneity makes a single global model unsuitable for many clients. This paper proposes federated clustering with adaptive personalization (FedCAP), a parameter-efficient personalized FL framework that separates cluster-level representation learning from client-level adaptation. Clients are grouped using training-only daily traffic profiles, after which an LSTM backbone is trained by FedAvg within each cluster. Each client then freezes the cluster backbone and optimizes a residual bottleneck adapter locally. The adapter contains 4241 trainable parameters, 6.19% of the 68,483-parameter three-feature backbone and prediction head, and personalization transmits no model updates. In a shared-seed-42 comparison across 11 methods and four public datasets, FedCAP ranks first or second in 12 of 16 dataset–metric combinations. Across five shared seeds, its mean MAE is 6.66%, 7.47%, 2.64%, and 3.86% below FedAvg on the Milan, Trentino, Bihar, and Taiwan datasets, respectively. Holm-adjusted paired t-tests identify 6 significant dataset–metric differences, whereas exact Wilcoxon tests are not significant because each comparison contains only five nonzero seed-matched pairs; the statistical evidence is therefore interpreted conservatively.