Loughborough University
Browse

File(s) under permanent embargo

Reason: Publisher requirement. Embargo will be lifted after publication.

Memory-facilitated joint-space shift adaptation in traffic forecasting

conference contribution
posted on 2024-03-19, 13:59 authored by Ye WeiYe Wei, Haitao HeHaitao He, Gerald SchaeferGerald Schaefer, Zhigang Ji, Yifan WangYifan Wang, Hui FangHui Fang

Traffic forecasting, crucial for intelligent transport systems, faces significant challenges from distribution shifts due to the dynamic nature of traffic patterns. Although normalisation approaches have been proposed to address distribution shifts in other time-series forecasting tasks, e.g., predicting electricity consumption load and estimating influenza-like illness patient numbers, they fall short in handling the complex spatial and temporal shifts in traffic data. In this paper, we propose a novel memory-facilitated joint-space shift adaptation framework, namely ST-Align, to address the problem in traffic forecasting.

ST-Align comprises two key components targeting the input and latent space, respectively: a memory-based data alignment module in the input-space, and an end-to-end memory network structure dedicated to alignment within the latent-space. This joint-space design enables our ST-Align framework to effectively capture and adapt to dynamic distribution shifts in both spatial and temporal dimensions, hence enhancing model performance.

Our extensive experiments on various real-world datasets and prediction backbones have demonstrated the robustness and generalisability of our method.

History

School

  • Architecture, Building and Civil Engineering
  • Science

Department

  • Computer Science

Published in

International Joint Conference on Neural Networks

Source

International Joint Conference on Neural Networks

Publisher

IEEE

Version

  • AM (Accepted Manuscript)

Publisher statement

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

2024-03-15

Language

  • en

Location

Yokohama, Japan

Event dates

30th June 2024 - 5th July 2024

Depositor

Ye Wei. Deposit date: 16 March 2024

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC