mlsanityData to 14 Oct 2026

Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion

arXiv 2508.00037 ↗First posted 31 Jul 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Networked urban systems facilitate the flow of people, resources, and services, and are essential for economic and social interactions. These systems often involve complex processes with unknown governing rules, observed by sensor-based time series. To aid decision-making in industrial and engineering contexts, data-driven predictive models are used to forecast spatiotemporal dynamics of urban systems. Current models such as graph neural networks have shown promise but face a trade-off between efficacy and efficiency due to computational demands. Hence, their applications in large-scale networks still require further efforts. This paper addresses this trade-off challenge by drawing inspiration from physical laws to inform essential model designs that align with fundamental principles and avoid architectural redundancy. By understanding both micro- and macro-processes, we present a principled interpretable neural diffusion scheme based on Transformer-like structures whose attention layers are induced by low-dimensional embeddings. The proposed scalable spatiotemporal Transformer (ScaleSTF), with linear complexity, is validated on large-scale urban systems including traffic flow, solar power, and smart meters, showing state-of-the-art performance and remarkable scalability. Our results constitute a fresh perspective on the dynamics prediction in large-scale urban networks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 47 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

29 of 47 references.

References · 29

  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  2. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  3. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  4. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  5. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  6. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  7. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  8. 2022Transformers in Time Series: A Surveycited by 497
  9. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  10. 2021GRAND: Graph Neural Diffusioncited by 258
  11. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  12. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 180
17 more
  1. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  2. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 137
  3. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  4. 2023LargeST: A Benchmark Dataset for Large-Scale Traffic Forecastingcited by 118
  5. 2022A Generalization of ViT/MLP-Mixer to Graphscited by 93
  6. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 87
  7. 2022Understanding convolution on graphs via energiescited by 59
  8. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  9. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  10. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  11. 2024COLA: Cross-city Mobility Transformer for Human Trajectory Simulationcited by 25
  12. 2023Do We Really Need Graph Neural Networks for Traffic Forecasting?cited by 20
  13. 2024Channel-Aware Low-Rank Adaptation in Time Series Forecastingcited by 12
  14. 2021A Lightweight and Accurate Spatial-Temporal Transformer for Traffic Forecastingcited by 9
  15. 2024UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Predictioncited by 7
  16. 2023STNet: Spatial and Temporal feature fusion network for change detection in remote sensing imagescited by 6
  17. 2025A Novel Scene Coupling Semantic Mask Network for Remote Sensing Image Segmentationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026PIMCST: Physics-Informed Multi-Phase Consensus and Spatio-Temporal Few-Shot Learning for Traffic Flow Forecastingcited by 1