A Global-Local Graph Attention Network for Traffic Forecasting
Quick Take
GLGAT enhances traffic forecasting by integrating global and local attention mechanisms in graph networks.
Key Points
- Addresses spatio-temporal correlations in traffic data.
- Utilizes pairwise encoding and event-based adjacency matrices.
- Outperforms state-of-the-art models on real-world datasets.
📖 Reader Mode
~2 min readAbstract:Traffic forecasting is a significant part of intelligent transportation systems. One of the critical challenges of traffic forecasting is to find spatio-temporal correlations. In recent years, graph convolutional networks and graph attention networks have replaced traditional statistical models to predict future traffic. However, it is complicated for both of them to allow vertices to have far different characters. To address this, we propose the Global-Local Graph Attention Network (GLGAT) with pairwise encoding and the event-based adjacency matrix. The GLGAT allows vertices to have a global attention matrix set for the whole graph and assigns local attention matrix sets to each vertex. Experiments on two real-world traffic datasets show that GLGAT can effectively capture spatio-temporal correlations and has competitive performance against other state-of-the-art baselines.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.16726 [cs.AI] |
| (or arXiv:2605.16726v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.16726 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tianchi Zhang [view email]
[v1]
Sat, 16 May 2026 00:28:59 UTC (32 KB)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →1d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.