Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction

TL;DR

This paper introduces a novel continuous-time, multi-level graph learning framework for pairwise origin-destination demand prediction in traffic systems, effectively capturing complex spatial-temporal dependencies.

Contribution

It proposes a continuous-time dynamic graph model with multi-level structure learning and cross-level fusion, advancing OD demand prediction accuracy over existing methods.

Findings

Outperforms state-of-the-art models on Beijing Subway dataset

Achieves higher prediction accuracy on New York Taxi data

Effectively models complex spatial-temporal dependencies

Abstract

Traffic demand forecasting by deep neural networks has attracted widespread interest in both academia and industry society. Among them, the pairwise Origin-Destination (OD) demand prediction is a valuable but challenging problem due to several factors: (i) the large number of possible OD pairs, (ii) implicitness of spatial dependence, and (iii) complexity of traffic states. To address the above issues, this paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD). Firstly, a continuous-time dynamic graph representation learning framework is constructed, which maintains a dynamic state vector for each traffic node (metro stations or taxi zones). The state vectors keep historical transaction information and are continuously updated according to the most recently happened transactions. Secondly, a multi-level structure learning module is proposed to model the spatial dependency of station-level nodes. It can not only exploit relations between nodes adaptively from data, but also share messages and representations via cluster-level and area-level virtual nodes. Lastly, a cross-level fusion module is designed to integrate multi-level memories and generate comprehensive node representations for the final prediction. Extensive experiments are conducted on two real-world datasets from Beijing Subway and New York Taxi, and the results demonstrate the superiority of our model against the state-of-the-art approaches.