Unsupervised Path Representation Learning with Curriculum Negative Sampling

Sean Bin Yang, Chenjuan Guo, Jilin Hu*, Jian Tang, Bin Yang

*Kontaktforfatter

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

8 Citationer (Scopus)

Abstrakt

Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific path representations in a supervised manner, which require a large amount of labeled training data and generalize poorly to other tasks. We propose an unsupervised learning framework Path InfoMax (PIM) to learn generic path representations that work for different downstream tasks. We first propose a curriculum negative sampling method, for each input path, to generate a small amount of negative paths, by following the principles of curriculum learning. Next, PIM employs mutual information maximization to learn path representations from both a global and a local view. In the global view, PIM distinguishes the representations of the input paths from those of the negative paths. In the local view, PIM distinguishes the input path representations from the representations of the nodes that appear only in the negative paths. This enables the learned path representations encode both global and local information at different scales. Extensive experiments on two downstream tasks, ranking score estimation and travel time estimation, using two road network datasets suggest that PIM significantly outperforms other unsupervised methods and is also able to be used as a pre-training method to enhance supervised path representation learning.

OriginalsprogEngelsk
TitelProceedings of the 30th International Joint Conference on Artificial Intelligence, IJCAI 2021
RedaktørerZhi-Hua Zhou
Antal sider7
ForlagInternational Joint Conferences on Artificial Intelligence
Publikationsdato2021
Sider3286-3292
ISBN (Elektronisk)978-0-9992411-9-6
DOI
StatusUdgivet - 2021
Begivenhed30th International Joint Conference on Artificial Intelligence, IJCAI 2021 - Virtual, Online, Canada
Varighed: 19 aug. 202127 aug. 2021

Konference

Konference30th International Joint Conference on Artificial Intelligence, IJCAI 2021
Land/OmrådeCanada
ByVirtual, Online
Periode19/08/202127/08/2021
SponsorInternational Joint Conferences on Artifical Intelligence (IJCAI)
NavnIJCAI International Joint Conference on Artificial Intelligence
ISSN1045-0823

Bibliografisk note

Publisher Copyright:
© 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.

Fingeraftryk

Dyk ned i forskningsemnerne om 'Unsupervised Path Representation Learning with Curriculum Negative Sampling'. Sammen danner de et unikt fingeraftryk.

Citationsformater