Modeling route representation with mixed-scale hierarchical transformer

• Main Authors: ZHANG, Hanyuan, CHEN, Yuqi, ZHANG, Xinyu, JIANG, Qize, LI, Liang, ZHENG, Baihua, SUN, Weiwei
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Spatial-temporal data modeling; road sensor network; self-attention model; Databases and Information Systems; OS and Networks
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/9168; https://doi.org/10.1109/ICASSP48485.2024.10446095
• 機構: Singapore Management University

Modeling route representation aims to obtain contextual representations of an entire route for various traffic-related tasks. In reality, spatial-temporal data often exhibits multi-scale characteristics, which are utilized by many studies to enhance their performance. However, there is still a lack of in-depth research on how to effectively incorporate the multi-scale spatial-temporal information into transformer structure to adequately model route representation. In this paper, we propose a novel hierarchical route representation framework called RouteMT, which effectively captures multi-scale spatial-temporal characteristics of routes and leverages a mixed-scale transformer architecture to fuse intra and interroute features. Experiments on real data confirm RouteMT’s superior performance and versatility.