English

Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks

Machine Learning 2024-09-11 v1

Abstract

Accurate prediction of traffic accidents across different times and regions is vital for public safety. However, existing methods face two key challenges: 1) Generalization: Current models rely heavily on manually constructed multi-view structures, like POI distributions and road network densities, which are labor-intensive and difficult to scale across cities. 2) Real-Time Performance: While some methods improve accuracy with complex architectures, they often incur high computational costs, limiting their real-time applicability. To address these challenges, we propose SSL-eKamba, an efficient self-supervised framework for traffic accident prediction. To enhance generalization, we design two self-supervised auxiliary tasks that adaptively improve traffic pattern representation through spatiotemporal discrepancy awareness. For real-time performance, we introduce eKamba, an efficient model that redesigns the Kolmogorov-Arnold Network (KAN) architecture. This involves using learnable univariate functions for input activation and applying a selective mechanism (Selective SSM) to capture multi-variate correlations, thereby improving computational efficiency. Extensive experiments on two real-world datasets demonstrate that SSL-eKamba consistently outperforms state-of-the-art baselines. This framework may also offer new insights for other spatiotemporal tasks. Our source code is publicly available at http://github.com/KevinT618/SSL-eKamba.

Keywords

Cite

@article{arxiv.2409.05933,
  title  = {Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks},
  author = {Xin Tan and Meng Zhao},
  journal= {arXiv preprint arXiv:2409.05933},
  year   = {2024}
}
R2 v1 2026-06-28T18:39:02.466Z