Dynamic Graph Representation Learning for Passenger Behavior Prediction

TL;DR

This paper introduces DyGPP, a dynamic graph-based model that captures evolving passenger-station interactions to improve behavior prediction in urban transportation systems.

Contribution

It proposes a novel dynamic graph framework that models passenger and station interactions over time, capturing complex temporal correlations.

Findings

DyGPP outperforms existing models in real-world datasets.

The model effectively captures temporal evolution of passenger behavior.

Dynamic graph representation improves prediction accuracy.

Abstract

Passenger behavior prediction aims to track passenger travel patterns through historical boarding and alighting data, enabling the analysis of urban station passenger flow and timely risk management. This is crucial for smart city development and public transportation planning. Existing research primarily relies on statistical methods and sequential models to learn from individual historical interactions, which ignores the correlations between passengers and stations. To address these issues, this paper proposes DyGPP, which leverages dynamic graphs to capture the intricate evolution of passenger behavior. First, we formalize passengers and stations as heterogeneous vertices in a dynamic graph, with connections between vertices representing interactions between passengers and stations. Then, we sample the historical interaction sequences for passengers and stations separately. We capture the temporal patterns from individual sequences and correlate the temporal behavior between the two sequences. Finally, we use an MLP-based encoder to learn the temporal patterns in the interactions and generate real-time representations of passengers and stations. Experiments on real-world datasets confirmed that DyGPP outperformed current models in the behavior prediction task, demonstrating the superiority of our model.