• Home
  • Search
  • STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation
  • Cite Icon1
  • https://doi.org/10.24963/ijcai.2025/382Copy DOI Icon

STAMImputer: Spatio-Temporal Attention MoE for Traffic Data Imputation

  • Sep 1, 2025
  • Yiming Wang +6 more
Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Traffic data imputation is fundamentally important to support various applications in intelligent transportation systems such as traffic flow prediction. However, existing time-to-space sequential methods often fail to effectively extract features in block-wise missing data scenarios. Meanwhile, the static graph structure for spatial feature propagation significantly constrains the model's flexibility in handling the distribution shift issue for the nonstationary traffic data. To address these issues, this paper proposes a Spatio-Temporal Attention Mixture of experts network named STAMImputer for traffic data imputation. Specifically, we introduce a Mixture of Experts (MoE) framework to capture latent spatio-temporal features and their influence weights, effectively imputing block missing. A novel Low-rank guided Sampling Graph ATtention (LrSGAT) mechanism is designed to dynamically balance the local and global correlations across road networks. The sampled attention vectors are utilized to generate dynamic graphs that capture real-time spatial correlations. Extensive experiments are conducted on four traffic datasets for evaluation. The result shows STAMImputer achieves significantly performance improvement compared with existing SOTA approaches. Our codes are available at https://github.com/RingBDStack/STAMImupter.

Similar Papers
  • Research Article

Types of ai algorithms used in traffic flow prediction

  • Apr 30, 2025
  • PAHTEI-Procedings of Azerbaijan High Technical Educational Institutions
  • Kamala Aliyeva Kamala Aliyeva
  • Research Article
  • Citations81

Spatial-Temporal Chebyshev Graph Neural Network for Traffic Flow Prediction in IoT-Based ITS

  • Jun 15, 2022
  • IEEE Internet of Things Journal
  • Biwei Yan +4
  • Conference Article
  • Citations6

Traffic Flow Prediction Based on Traffic and Meteorological Data Fusion in Non-stationary Environments

  • Dec 01, 2021
  • Hongbo Xiao +3
  • Research Article
  • Citations1

Traffic Flow Prediction Based on VMD-ARO-BiLSTM

  • Aug 12, 2024
  • International Journal of Computer Science and Information Technology
  • Haoxu Wang
  • Research Article
  • Citations32

Dynamic multi-scale spatial–temporal graph convolutional network for traffic flow prediction

  • Apr 27, 2024
  • Future Generation Computer Systems
  • Na Hu +5
  • Conference Article
  • Citations10

Supervised Deep Learning Based for Traffic Flow Prediction

  • Oct 01, 2018
  • Hendrik Tampubolon +1
  • Research Article
  • Citations1

Traffic Flow Prediction Framework That Can Appropriately Process the Noise, Volatility, and Nonlinearity in Traffic Flow Data

  • Jan 01, 2025
  • International Journal of Intelligent Systems
  • Yingping Tang +3
  • Book Chapter
  • Citations54

Deep Bi-directional Long Short-Term Memory Model for Short-Term Traffic Flow Prediction

  • Jan 01, 2017
  • Jingyuan Wang +2
  • Research Article
  • Citations7

Fuzzy Inspired Deep Belief Network for the Traffic Flow Prediction in Intelligent Transportation System Using Flow Strength Indicators.

  • Jul 06, 2020
  • Big data
  • Shiju George +1
  • Research Article
  • Citations5

Flow Direction Level Traffic Flow Prediction Based on a GCN-LSTM Combined Model

  • Jan 01, 2023
  • Intelligent Automation & Soft Computing
  • Fulu Wei +5
  • Conference Article

Multi-scale Fusion Dynamic Graph Neural Network For Traffic Flow Prediction

  • Sep 15, 2023
  • Wenchao Weng +4
  • Research Article
  • Citations20

Traffic flow prediction using multi-view graph convolution and masked attention mechanism

  • Aug 13, 2022
  • Computer Communications
  • Lingqiang Chen +3
  • Research Article
  • Citations2

Traffic Flow Prediction Based on Large Language Models and Future Development Directions

  • Jan 01, 2025
  • ITM Web of Conferences
  • Muhua Zhang +1
  • Book Chapter
  • Citations3

Generative Adversarial Network for Imputation of Road Network Traffic State Data

  • Jan 01, 2022
  • Dongwei Xu +3
  • Conference Article
  • Citations10

Improved LSTM Based on Attention Mechanism for Short-term Traffic Flow Prediction

  • Sep 01, 2020
  • Dejun Chen +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.