mlsanityData to 7 Oct 2026

Fast Temporal Wavelet Graph Neural Networks

arXiv 2302.08643 ↗First posted 17 Feb 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal signals forecasting plays an important role in numerous domains, especially in neuroscience and transportation. The task is challenging due to the highly intricate spatial structure, as well as the non-linear temporal dynamics of the network. To facilitate reliable and timely forecast for the human brain and traffic networks, we propose the Fast Temporal Wavelet Graph Neural Networks (FTWGNN) that is both time- and memory-efficient for learning tasks on timeseries data with the underlying graph structure, thanks to the theories of multiresolution analysis and wavelet theory on discrete spaces. We employ Multiresolution Matrix Factorization (MMF) (Kondor et al., 2014) to factorize the highly dense graph structure and compute the corresponding sparse wavelet basis that allows us to construct fast wavelet convolution as the backbone of our novel architecture. Experimental results on real-world PEMS-BAY, METR-LA traffic datasets and AJILE12 ECoG dataset show that FTWGNN is competitive with the state-of-the-arts while maintaining a low computational footprint. Our PyTorch implementation is publicly available at https://github.com/HySonLab/TWGNN

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

19 of 48 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  6. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  7. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  8. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 330
  9. 2021GRAND: Graph Neural Diffusioncited by 258
  10. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  11. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 179
  12. 2021Graph Neural Networks in Network Neurosciencecited by 91
7 more
  1. 2020Foreseeing Brain Graph Evolution Over Time Using Deep Adversarial Network Normalizercited by 11
  2. 2016Fej'er-monotone hybrid steepest descent method for affinely constrained and composite convex minimization taskscited by 6
  3. 2017Multiresolution Kernel Approximation for Gaussian Process Regressioncited by 6
  4. 2020Residual Embedding Similarity-Based Network Selection for Predicting Brain Network Evolution Trajectory from a Single Observationcited by 6
  5. 2017The Incremental Multiresolution Matrix Factorization Algorithmcited by 4
  6. 2021An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future workscited by 3
  7. 2015Parallel MMF: a Multiresolution Approach to Matrix Computationcited by 1

Built on by

Cited by year

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

6 papers.

  1. 2023Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's studycited by 6
  2. 2024TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understandingcited by 2
  3. 2023Multimodal Graph Learning for Modeling Emerging Pandemics with Big Datacited by 1
  4. 2024SAMSA: Efficient Transformer for Many Data Modalitiescited by 0
  5. 2024Range-aware Positional Encoding via High-order Pretraining: Theory and Practicecited by 0
  6. 2025RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Networkcited by 0