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

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of the 2018 IEEE International Conference on Big Data
Number of pages10
PublisherIEEE
Publication date2018
Pages3421-3430
ISBN (Electronic)978-1-5386-5035-6
DOIs
Publication statusPublished - 2018
Event2018 IEEE International Conference on Big Data - Seattle, United States
Duration: 10 Dec 201813 Dec 2018

Conference

Conference2018 IEEE International Conference on Big Data
CountryUnited States
CitySeattle
Period10/12/201813/12/2018

Fingerprint

Learning systems
Availability

Keywords

  • road network
  • machine learning
  • feature learning
  • network embedding

Cite this

@inproceedings{b391f9dee0f74d9a8818794b84b07ae7,
title = "On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network",
abstract = "Road networks are a type of spatial network, whereedges may be associated with qualitative information such asroad type and speed limit. Unfortunately, such information isoften incomplete; for instance, OpenStreetMap only has speedlimits for 13{\%} of all Danish road segments. This is problematicfor analysis tasks that rely on such information for machinelearning. To enable machine learning in such circumstances, onemay consider the application of network embedding methods toextract structural information from the network. However, thesemethods have so far mostly been used in the context of socialnetworks, which differ significantly from road networks in termsof, e.g., node degree and level of homophily (which are key tothe performance of many network embedding methods).We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in roadnetworks. Due to the often limited availability of informationon other relevant road characteristics, the analysis focuses onleveraging the spatial network structure. Our results suggest thatnetwork embedding methods can indeed be used for derivingrelevant network features (that may, e.g, be used for predictingspeed limits), but that the qualities of the embeddings differ fromembeddings for social networks.",
keywords = "road network, machine learning, feature learning, network embedding",
author = "Jepsen, {Tobias S.} and Jensen, {Christian S{\o}ndergaard} and Nielsen, {Thomas Dyhre} and Kristian Torp",
year = "2018",
doi = "10.1109/BigData.2018.8622416",
language = "English",
pages = "3421--3430",
booktitle = "Proceedings of the 2018 IEEE International Conference on Big Data",
publisher = "IEEE",
address = "United States",

}

Jepsen, TS, Jensen, CS, Nielsen, TD & Torp, K 2018, On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network. in Proceedings of the 2018 IEEE International Conference on Big Data. IEEE, pp. 3421-3430, 2018 IEEE International Conference on Big Data, Seattle, United States, 10/12/2018. https://doi.org/10.1109/BigData.2018.8622416

On Network Embedding for Machine Learning on Road Networks : A Case Study on the Danish Road Network. / Jepsen, Tobias S.; Jensen, Christian Søndergaard; Nielsen, Thomas Dyhre; Torp, Kristian.

Proceedings of the 2018 IEEE International Conference on Big Data. IEEE, 2018. p. 3421-3430.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - On Network Embedding for Machine Learning on Road Networks

T2 - A Case Study on the Danish Road Network

AU - Jepsen, Tobias S.

AU - Jensen, Christian Søndergaard

AU - Nielsen, Thomas Dyhre

AU - Torp, Kristian

PY - 2018

Y1 - 2018

N2 - Road networks are a type of spatial network, whereedges may be associated with qualitative information such asroad type and speed limit. Unfortunately, such information isoften incomplete; for instance, OpenStreetMap only has speedlimits for 13% of all Danish road segments. This is problematicfor analysis tasks that rely on such information for machinelearning. To enable machine learning in such circumstances, onemay consider the application of network embedding methods toextract structural information from the network. However, thesemethods have so far mostly been used in the context of socialnetworks, which differ significantly from road networks in termsof, e.g., node degree and level of homophily (which are key tothe performance of many network embedding methods).We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in roadnetworks. Due to the often limited availability of informationon other relevant road characteristics, the analysis focuses onleveraging the spatial network structure. Our results suggest thatnetwork embedding methods can indeed be used for derivingrelevant network features (that may, e.g, be used for predictingspeed limits), but that the qualities of the embeddings differ fromembeddings for social networks.

AB - Road networks are a type of spatial network, whereedges may be associated with qualitative information such asroad type and speed limit. Unfortunately, such information isoften incomplete; for instance, OpenStreetMap only has speedlimits for 13% of all Danish road segments. This is problematicfor analysis tasks that rely on such information for machinelearning. To enable machine learning in such circumstances, onemay consider the application of network embedding methods toextract structural information from the network. However, thesemethods have so far mostly been used in the context of socialnetworks, which differ significantly from road networks in termsof, e.g., node degree and level of homophily (which are key tothe performance of many network embedding methods).We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in roadnetworks. Due to the often limited availability of informationon other relevant road characteristics, the analysis focuses onleveraging the spatial network structure. Our results suggest thatnetwork embedding methods can indeed be used for derivingrelevant network features (that may, e.g, be used for predictingspeed limits), but that the qualities of the embeddings differ fromembeddings for social networks.

KW - road network

KW - machine learning

KW - feature learning

KW - network embedding

UR - https://ieeexplore.ieee.org/document/8622416

U2 - 10.1109/BigData.2018.8622416

DO - 10.1109/BigData.2018.8622416

M3 - Article in proceeding

SP - 3421

EP - 3430

BT - Proceedings of the 2018 IEEE International Conference on Big Data

PB - IEEE

ER -