mlsanityData to 14 Oct 2026

Do We Really Need Graph Neural Networks for Traffic Forecasting?

arXiv 2301.12603 ↗First posted 30 Jan 2023cs.LG cs.SIcited by 20

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal graph neural networks (STGNN) have become the most popular solution to traffic forecasting. While successful, they rely on the message passing scheme of GNNs to establish spatial dependencies between nodes, and thus inevitably inherit GNNs' notorious inefficiency. Given these facts, in this paper, we propose an embarrassingly simple yet remarkably effective spatio-temporal learning approach, entitled SimST. Specifically, SimST approximates the efficacies of GNNs by two spatial learning techniques, which respectively model local and global spatial correlations. Moreover, SimST can be used alongside various temporal models and involves a tailored training strategy. We conduct experiments on five traffic benchmarks to assess the capability of SimST in terms of efficiency and effectiveness. Empirical results show that SimST improves the prediction throughput by up to 39 times compared to more sophisticated STGNNs while attaining comparable performance, which indicates that GNNs are not the only option for spatial modeling in traffic forecasting.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 30 Jan 2023.

Builds on

27 of 43 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  7. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  9. 2017Neural Collaborative Filteringcited by 1,111
  10. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  11. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 631
  12. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
15 more
  1. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  2. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  3. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  4. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  5. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  6. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  7. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  8. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  9. 2021Spatial-Temporal Graph ODE Networks for Traffic Flow Forecastingcited by 210
  10. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 152
  11. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  12. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  13. 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
  14. 2021When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?cited by 36
  15. 2022NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 3; 2025: 3; 2026: 4.

20 papers.

Sort:

  1. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  2. 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
  3. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  4. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  5. 2023Cross-city Few-Shot Traffic Forecasting via Traffic Pattern Bankcited by 24
  6. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 22
  7. 2024STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecastingcited by 9
  8. 2023STG4Traffic: A Survey and Benchmark of Spatial-Temporal Graph Neural Networks for Traffic Predictioncited by 8
  9. 2024SAGDFN: A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecastingcited by 8
  10. 2023Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scalecited by 3
  11. 2023TSPP: A Unified Benchmarking Tool for Time-series Forecastingcited by 2
  12. 2024PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecastingcited by 2
8 more
  1. 2026Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Modelscited by 2
  2. 2025Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusioncited by 1
  3. 2026Do We Really Need Adaptive Global Spatial Attention for Traffic Forecasting?cited by 1
  4. 2023Spatial-Temporal Hypergraph Neural Network for Traffic Forecastingcited by 0
  5. 2025Channel-Independent Federated Traffic Predictioncited by 0
  6. 2025Adaptive Graph Pruning with Sudden-Events Evaluation for Traffic Prediction using Online Semi-Decentralized ST-GNNscited by 0
  7. 2026Positional-aware Spatio-Temporal Network for Large-Scale Traffic Predictioncited by 0
  8. 2026Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depthcited by 0