mlsanityData to 14 Oct 2026

A Visual Analytics System for Improving Attention-based Traffic Forecasting Models

arXiv 2208.04350 ↗First posted 8 Aug 2022cs.HC cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

With deep learning (DL) outperforming conventional methods for different tasks, much effort has been devoted to utilizing DL in various domains. Researchers and developers in the traffic domain have also designed and improved DL models for forecasting tasks such as estimation of traffic speed and time of arrival. However, there exist many challenges in analyzing DL models due to the black-box property of DL models and complexity of traffic data (i.e., spatio-temporal dependencies). Collaborating with domain experts, we design a visual analytics system, AttnAnalyzer, that enables users to explore how DL models make predictions by allowing effective spatio-temporal dependency analysis. The system incorporates dynamic time warping (DTW) and Granger causality tests for computational spatio-temporal dependency analysis while providing map, table, line chart, and pixel views to assist user to perform dependency and model behavior analysis. For the evaluation, we present three case studies showing how AttnAnalyzer can effectively explore model behaviors and improve model performance in two different road networks. We also provide domain expert feedback.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 82 references that are in the map. First posted on arXiv 8 Aug 2022.

Builds on

30 of 82 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  5. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  6. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  7. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  8. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  9. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  10. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  11. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
  12. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
18 more
  1. 2018Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Predictioncited by 122
  2. 2018Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontierscited by 117
  3. 2019FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learningcited by 93
  4. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  5. 2019Shape and Time Distortion Loss for Training Deep Time Series Forecasting Modelscited by 70
  6. 2018Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Modelscited by 69
  7. 2017ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Modelscited by 56
  8. 2016Towards Better Analysis of Deep Convolutional Neural Networkscited by 51
  9. 2020Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Modelscited by 49
  10. 2017Understanding Hidden Memories of Recurrent Neural Networkscited by 44
  11. 2018GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentationcited by 41
  12. 2020Analyzing the Noise Robustness of Deep Neural Networkscited by 31
  13. 2019SANVis: Visual Analytics for Understanding Self-Attention Networkscited by 21
  14. 2017Spectral clustering in the dynamic stochastic block modelcited by 12
  15. 2018HyperST-Net: Hypernetworks for Spatio-Temporal Forecastingcited by 11
  16. 2020Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analyticscited by 6
  17. 2021An Empirical Experiment on Deep Learning Models for Predicting Traffic Datacited by 4
  18. 2019An Automated Spectral Clustering for Multi-scale Datacited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 1.

6 papers.

  1. 2023How Does Attention Work in Vision Transformers? A Visual Analytics Attemptcited by 30
  2. 2023Visual Analytics For Machine Learning: A Data Perspective Surveycited by 25
  3. 2024TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Expertscited by 18
  4. 2023ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinementcited by 5
  5. 2025A Survey of Multi-sensor Fusion Perception for Embodied AI: Background, Methods, Challenges and Prospectscited by 5
  6. 2024Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecastingcited by 3