On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network

TL;DR

This paper investigates the application of network embedding methods, specifically node2vec, to road networks, demonstrating their potential for extracting useful features despite structural differences from social networks.

Contribution

It provides an analysis of network embedding effectiveness on road networks, highlighting differences from social network embeddings and focusing on structural information for machine learning.

Findings

Embeddings can be used to derive relevant features for road networks.

Network embedding qualities differ from those in social networks.

Potential for predicting road attributes like speed limits.

Abstract

Road networks are a type of spatial network, where edges may be associated with qualitative information such as road type and speed limit. Unfortunately, such information is often incomplete; for instance, OpenStreetMap only has speed limits for 13% of all Danish road segments. This is problematic for analysis tasks that rely on such information for machine learning. To enable machine learning in such circumstances, one may consider the application of network embedding methods to extract structural information from the network. However, these methods have so far mostly been used in the context of social networks, which differ significantly from road networks in terms of, e.g., node degree and level of homophily (which are key to the performance of many network embedding methods). We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in road networks. Due to the often limited availability of information on other relevant road characteristics, the analysis focuses on leveraging the spatial network structure. Our results suggest that network embedding methods can indeed be used for deriving relevant network features (that may, e.g, be used for predicting speed limits), but that the qualities of the embeddings differ from embeddings for social networks.