mlsanityData to 14 Oct 2026

ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics

arXiv 2605.09676 ↗First posted 10 May 2026cs.LG cs.AI nlin.CDcited by 0

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal graph neural networks (STGNNs) are widely used for short-term forecasting in dynamic physical systems such as traffic and weather. However, the prevailing evaluation practice uses real world benchmark data sets in a single domain with a single fixed holdout splits, making it difficult to compare architectures across different dynamical regimes. We introduce ChaosNetBench (CNB), a synthetic benchmark dataset and evaluation framework for studying STGNN performance under controlled multidimensional chaotic dynamics. CNB is built on a lattice of coupled standard maps with independently tunable local chaos (K), coupling strength (varepsilon), and system size (N), providing known topology and known dynamics across 96 system instances and 9,600 trajectories. We introduce chaos indicators, evaluation metrics and a protocol to analyze and compare the capacity of STGNN architectures to deal with different levels of local and global chaos. We illustrate the usage of the framework by analyzing 13 architectures (5 STGNNs and 8 non-graph baselines). The results reveal a regime dependent transition in which non-graph baselines (TCN, N-BEATS, iTransformer) remain competitive when there is low local chaos, while STGNNs (e.g., Graph WaveNet, D2STGNN, STAEformer) are generally more resilient to higher levels of local and global chaos. CNB provides a practical, reusable testbed for systematically comparing and analyzing the capacity of STGNN architectures to handle different levels of local and global chaos.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 55 references that are in the map. First posted on arXiv 10 May 2026.

Builds on

25 of 55 references.

References · 25

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  6. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  7. 2019Hamiltonian Neural Networkscited by 712
  8. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  9. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  10. 2016Temporal Convolutional Networks for Action Segmentation and Detectioncited by 508
  11. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 413
  12. 2020Lagrangian Neural Networkscited by 398
13 more
  1. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  2. 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
  3. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  4. 2021Chaos as an interpretable benchmark for forecasting and data-driven modellingcited by 88
  5. 2024Croissant: A Metadata Format for ML-Ready Datasetscited by 81
  6. 2021Synthetic Benchmarks for Scientific Research in Explainable Machine Learningcited by 59
  7. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  8. 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Predictioncited by 43
  9. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  10. 2023Model scale versus domain knowledge in statistical forecasting of chaotic systemscited by 27
  11. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  12. 2022AZ-whiteness test: a test for uncorrelated noise on spatio-temporal graphscited by 5
  13. 2026Position: A Dynamical Systems Perspective is Needed to Advance Time Series Modelingcited by 4

Built on by

Not cited yet.