Latent Factorization of Tensors with Threshold Distance Weighted Loss for Traffic Data Estimation

TL;DR

This paper introduces a novel tensor factorization method with a threshold distance weighted loss to improve traffic data imputation, effectively reducing outlier influence and enhancing prediction accuracy and efficiency.

Contribution

The paper proposes the TDWLFT model, incorporating a new loss function that mitigates outlier effects in tensor factorization for traffic data estimation.

Findings

TDWLFT outperforms existing methods in accuracy

The model is more robust to outliers

It demonstrates improved computational efficiency

Abstract

Intelligent transportation systems (ITS) rely heavily on complete and high-quality spatiotemporal traffic data to achieve optimal performance. Nevertheless, in real-word traffic data collection processes, issues such as communication failures and sensor malfunctions often lead to incomplete or corrupted datasets, thereby posing significant challenges to the advancement of ITS. Among various methods for imputing missing spatiotemporal traffic data, the latent factorization of tensors (LFT) model has emerged as a widely adopted and effective solution. However, conventional LFT models typically employ the standard L2-norm in their learning objective, which makes them vulnerable to the influence of outliers. To overcome this limitation, this paper proposes a threshold distance weighted (TDW) loss-incorporated Latent Factorization of Tensors (TDWLFT) model. The proposed loss function effectively reduces the model's sensitivity to outliers by assigning differentiated weights to individual samples. Extensive experiments conducted on two traffic speed datasets sourced from diverse urban environments confirm that the proposed TDWLFT model consistently outperforms state-of-the-art approaches in terms of both in both prediction accuracy and computational efficiency.