← Back to all news
arXiv AI By Jiawen Chen, Qi Shao, Yongjian Chang, Mingtong Zhou, Duxin Chen, Wenwu Yu

STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data Forecasting

Read the original on arXiv AI →

STHMoE is a Spatio‑Temporal Hypergraph‑Enhanced Mixture of Experts framework designed for urban traffic forecasting. It separates traffic dynamics into frequency‑, time‑, spatial‑, and higher‑order representations, each handled by a prompt‑guided expert built on a partially frozen large language model. The higher‑order expert uses an adaptive hypergraph module to learn evolving spatial structures, while an entropy‑aware router balances expert usage and fuses outputs, achieving competitive results on ten real‑world traffic benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 18

FedeRICo: Federated Region-Influenced Coupling for Traffic Flow Prediction

FedeRICo is a federated traffic forecasting framework that addresses heterogeneity across client sensor subgraphs by combining gradient-level collaboration with boundary-aware residual communication. It uses a dual-branch architecture: a globally guided branch for transferable forecasting structure and a private residual branch that preserves client-specific corrections and incorporates boundary residual signals. Experiments on four real-world traffic benchmarks show that FedeRICo outperforms state‑of‑the‑art federated spatial‑temporal baselines while keeping training runtime competitive.

By Fermin Orozco, Man Luo, Johan Wahlstr\"om
benchmarkssafety
More like this →
arXiv AI
Sep 24

Learning Local Heterogeneity and Cross-Region Context for Large-Scale Traffic Forecasting

The paper introduces LoReST, a Local-Region Spatial Temporal network designed for large-scale traffic forecasting. LoReST captures local spatial heterogeneity by relation-aware aggregation within node neighborhoods and incorporates cross-region context through mean pooling, inter-region attention, and broadcasting back to nodes. Experiments on the LargeST benchmark demonstrate significant improvements, reducing MAE, RMSE, and MAPE by 4.78%, 3.60%, and 5.75% respectively.

By Qi Feng, Zidong Wang, Bo Li, Xiaoguang Gao, Jiayu Zhang, Chenfeng Wang, Kaifang Wan
benchmarks
More like this →