Geographical Information Alignment Boosts Traffic Analysis via Transpose Cross-attention

TL;DR

This paper introduces a Geographic Information Alignment (GIA) module with a transpose cross-attention mechanism to improve traffic accident prediction by effectively integrating geographic position data into GNN models, achieving significant performance gains.

Contribution

The paper proposes a novel GIA module with transpose cross-attention that efficiently fuses geographic and node features, addressing computational challenges in large-scale traffic data analysis.

Findings

Achieves 1.3% to 10.9% F1 score improvements

Attains 0.3% to 4.8% AUC gains

Effective in both accident occurrence and severity prediction

Abstract

Traffic accident prediction is crucial for enhancing road safety and mitigating congestion, and recent Graph Neural Networks (GNNs) have shown promise in modeling the inherent graph-based traffic data. However, existing GNN- based approaches often overlook or do not explicitly exploit geographic position information, which often plays a critical role in understanding spatial dependencies. This is also aligned with our observation, where accident locations are often highly relevant. To address this issue, we propose a plug-in-and-play module for common GNN frameworks, termed Geographic Information Alignment (GIA). This module can efficiently fuse the node feature and geographic position information through a novel Transpose Cross-attention mechanism. Due to the large number of nodes for traffic data, the conventional cross-attention mechanism performing the node-wise alignment may be infeasible in computation-limited resources. Instead, we take the transpose operation for Query, Key, and Value in the Cross-attention mechanism, which substantially reduces the computation cost while maintaining sufficient information. Experimental results for both traffic occurrence prediction and severity prediction (severity levels based on the interval of recorded crash counts) on large-scale city-wise datasets confirm the effectiveness of our proposed method. For example, our method can obtain gains ranging from 1.3% to 10.9% in F1 score and 0.3% to 4.8% in AUC.