Partitioned Graph Convolution Using Adversarial and Regression Networks for Road Travel Speed Prediction

TL;DR

This paper introduces a novel graph convolution framework with adversarial and regression networks for predicting travel speeds on road networks, especially effective for large, sparse, and skewed datasets like the Danish road network.

Contribution

The paper proposes a partitioned graph convolution approach with adversarial regularization for accurate travel speed prediction on large-scale, sparse road networks, addressing graph size and data sparsity challenges.

Findings

Achieved 71.5% accuracy and 78.5% correlation in speed histogram prediction.

Partitioning into 100 clusters improves model performance.

Partitioning enhances prediction accuracy compared to fewer clusters.

Abstract

Access to quality travel time information for roads in a road network has become increasingly important with the rising demand for real-time travel time estimation for paths within road networks. In the context of the Danish road network (DRN) dataset used in this paper, the data coverage is sparse and skewed towards arterial roads, with a coverage of 23.88% across 850,980 road segments, which makes travel time estimation difficult. Existing solutions for graph-based data processing often neglect the size of the graph, which is an apparent problem for road networks with a large amount of connected road segments. To this end, we propose a framework for predicting road segment travel speed histograms for dataless edges, based on a latent representation generated by an adversarially regularized convolutional network. We apply a partitioning algorithm to divide the graph into dense subgraphs, and then train a model for each subgraph to predict speed histograms for the nodes. The framework achieves an accuracy of 71.5% intersection and 78.5% correlation on predicting travel speed histograms using the DRN dataset. Furthermore, experiments show that partitioning the dataset into clusters increases the performance of the framework. Specifically, partitioning the road network dataset into 100 clusters, with approximately 500 road segments in each cluster, achieves a better performance than when using 10 and 20 clusters.