Saved in:
Bibliographic Details
Main Authors: Wang, Guangyu, Chen, Yujie, Gao, Ming, Wu, Zhiqiao, Tang, Jiafu, Zhao, Jiabi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17440
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929516080791552
author Wang, Guangyu
Chen, Yujie
Gao, Ming
Wu, Zhiqiao
Tang, Jiafu
Zhao, Jiabi
author_facet Wang, Guangyu
Chen, Yujie
Gao, Ming
Wu, Zhiqiao
Tang, Jiafu
Zhao, Jiabi
contents Accurate traffic prediction faces significant challenges, necessitating a deep understanding of both temporal and spatial cues and their complex interactions across multiple variables. Recent advancements in traffic prediction systems are primarily due to the development of complex sequence-centric models. However, existing approaches often embed multiple variables and spatial relationships at each time step, which may hinder effective variable-centric learning, ultimately leading to performance degradation in traditional traffic prediction tasks. To overcome these limitations, we introduce variable-centric and prior knowledge-centric modeling techniques. Specifically, we propose a Heterogeneous Mixture of Experts (TITAN) model for traffic flow prediction. TITAN initially consists of three experts focused on sequence-centric modeling. Then, designed a low-rank adaptive method, TITAN simultaneously enables variable-centric modeling. Furthermore, we supervise the gating process using a prior knowledge-centric modeling strategy to ensure accurate routing. Experiments on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate that TITAN effectively captures variable-centric dependencies while ensuring accurate routing. Consequently, it achieves improvements in all evaluation metrics, ranging from approximately 4.37\% to 11.53\%, compared to previous state-of-the-art (SOTA) models. The code is open at \href{https://github.com/sqlcow/TITAN}{https://github.com/sqlcow/TITAN}.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17440
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction
Wang, Guangyu
Chen, Yujie
Gao, Ming
Wu, Zhiqiao
Tang, Jiafu
Zhao, Jiabi
Artificial Intelligence
Accurate traffic prediction faces significant challenges, necessitating a deep understanding of both temporal and spatial cues and their complex interactions across multiple variables. Recent advancements in traffic prediction systems are primarily due to the development of complex sequence-centric models. However, existing approaches often embed multiple variables and spatial relationships at each time step, which may hinder effective variable-centric learning, ultimately leading to performance degradation in traditional traffic prediction tasks. To overcome these limitations, we introduce variable-centric and prior knowledge-centric modeling techniques. Specifically, we propose a Heterogeneous Mixture of Experts (TITAN) model for traffic flow prediction. TITAN initially consists of three experts focused on sequence-centric modeling. Then, designed a low-rank adaptive method, TITAN simultaneously enables variable-centric modeling. Furthermore, we supervise the gating process using a prior knowledge-centric modeling strategy to ensure accurate routing. Experiments on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate that TITAN effectively captures variable-centric dependencies while ensuring accurate routing. Consequently, it achieves improvements in all evaluation metrics, ranging from approximately 4.37\% to 11.53\%, compared to previous state-of-the-art (SOTA) models. The code is open at \href{https://github.com/sqlcow/TITAN}{https://github.com/sqlcow/TITAN}.
title A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2409.17440