MHGNet: Multi-Heterogeneous Graph Neural Network for Traffic Prediction

TL;DR

This paper introduces MHGNet, a novel multi-heterogeneous graph neural network that effectively models complex traffic data, capturing diverse patterns and improving prediction accuracy in intelligent transportation systems.

Contribution

It proposes a new framework for modeling multi-heterogeneous graphs in traffic prediction, including modules for pattern decoupling, clustering, and spatiotemporal fusion, which outperform existing methods.

Findings

Superior performance on four benchmark datasets

Effective clustering of nodes by type and pattern

Enhanced modeling of multi-heterogeneous traffic data

Abstract

In recent years, traffic flow prediction has played a crucial role in the management of intelligent transportation systems. However, traditional forecasting methods often model non-Euclidean low-dimensional traffic data as a simple graph with single-type nodes and edges, failing to capture similar trends among nodes of the same type. To address this limitation, this paper proposes MHGNet, a novel framework for modeling spatiotemporal multi-heterogeneous graphs. Within this framework, the STD Module decouples single-pattern traffic data into multi-pattern traffic data through feature mappings of timestamp embedding matrices and node embedding matrices. Subsequently, the Node Clusterer leverages the Euclidean distance between nodes and different types of limit points to perform clustering with O(N) time complexity. The nodes within each cluster undergo residual subgraph convolution within the spatiotemporal fusion subgraphs generated by the DSTGG Module, followed by processing in the SIE Module for node repositioning and redistribution of weights. To validate the effectiveness of MHGNet, this paper conducts extensive ablation studies and quantitative evaluations on four widely used benchmarks, demonstrating its superior performance.