Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting

TL;DR

This paper introduces LSTAN-GERPE, a lightweight model that combines spatio-temporal attention, graph embedding, and rotational position encoding to improve traffic forecasting accuracy.

Contribution

The study proposes a novel spatio-temporal attention network with optimized rotational position encoding and geographical embeddings for enhanced traffic prediction.

Findings

Achieves higher accuracy on PeMS04 and PeMS08 datasets.

Effectively captures long-range traffic dynamics.

Systematic optimization of position encoding improves model performance.

Abstract

Traffic forecasting is a key task in the field of Intelligent Transportation Systems. Recent research on traffic forecasting has mainly focused on combining graph neural networks (GNNs) with other models. However, GNNs only consider short-range spatial information. In this study, we present a novel model termed LSTAN-GERPE (Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding). This model leverages both Temporal and Spatial Attention mechanisms to effectively capture long-range traffic dynamics. Additionally, the optimal frequency for rotational position encoding is determined through a grid search approach in both the spatial and temporal attention mechanisms. This systematic optimization enables the model to effectively capture complex traffic patterns. The model also enhances feature representation by incorporating geographical location maps into the spatio-temporal embeddings. Without extensive feature engineering, the proposed method in this paper achieves advanced accuracy on the real-world traffic forecasting datasets PeMS04 and PeMS08.