MHGNet: Multi-Heterogeneous Graph Neural Network for Traffic Prediction

2025-01-07

AI Summary

To address the challenge of modeling complex heterogeneous network structures and multimodal spatiotemporal dependencies in traffic flow forecasting for intelligent transportation systems, this paper proposes a novel heterogeneous graph neural network framework. Departing from conventional single-graph modeling paradigms, it explicitly captures multiple node types, semantically rich edges, and dynamic spatiotemporal relationships. Key innovations include spatiotemporal-derivative (STD) feature disentanglement, O(N) scalable node clustering, residual subgraph convolution, and node relocation. The framework integrates timestamp/node embedding mapping, Euclidean-distance-driven clustering, dynamic spatiotemporal fusion subgraph generation (DSTGG), and spatial information enhancement (SIE). Extensive experiments on four mainstream benchmarks demonstrate significant improvements over state-of-the-art methods. Ablation studies validate the effectiveness of each component, confirming that the framework achieves both high prediction accuracy and superior computational efficiency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

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.

Problem

• Traffic Flow Prediction
• Complex Network Patterns
• Intelligent Transportation Management

Innovation

• MHGNet
• Multi-type Graph Neural Network
• Traffic Flow Prediction