Deakin University
Browse

File(s) under permanent embargo

MetaER-TTE: An Adaptive Meta-learning Model for En Route Travel Time Estimation

conference contribution
posted on 2023-02-13, 03:07 authored by Y Fan, J Xu, R Zhou, Jianxin LiJianxin Li, K Zheng, L Chen, C Liu
En route travel time estimation (ER-TTE) aims to predict the travel time on the remaining route. Since the traveled and remaining parts of a trip usually have some common characteristics like driving speed, it is desirable to explore these characteristics for improved performance via effective adaptation. This yet faces the severe problem of data sparsity due to the few sampled points in a traveled partial trajectory. Since trajectories with different contextual information tend to have different characteristics, the existing meta-learning methods for ER-TTE cannot fit each trajectory well because it uses the same model for all trajectories. To this end, we propose a novel adaptive meta-learning model called MetaER-TTE. Particularly, we utilize soft-clustering and derive cluster-aware initialized parameters to better transfer the shared knowledge across trajectories with similar contextual information. In addition, we adopt a distribution-aware approach for adaptive learning rate optimization, so as to avoid task-overfitting which will occur when guiding the initial parameters with a fixed learning rate for tasks under imbalanced distribution. Finally, we conduct comprehensive experiments to demonstrate the superiority of MetaER-TTE.

History

Pagination

2023-2029

Location

Vienna, Austria

Start date

2022-07-23

End date

2022-07-29

ISSN

1045-0823

ISBN-13

9781956792003

Language

English

Publication classification

E1 Full written paper - refereed

Title of proceedings

IJCAI-ECAI 2022 : Proceedings of the International Joint Conference on Artificial Intelligence and European Conference on Artificial Intelligence 2022

Event

International Joint Conference on Artificial Intelligence and European Conference on Artificial Intelligence. Joint conference (31st/25th : 2022 : Vienna, Austria)

Publisher

IJCAI-ECAI

Place of publication

Vienna, Austria

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC