# Fast Temporal Wavelet Graph Neural Networks

arXiv: https://arxiv.org/abs/2302.08643 · HTML: https://mlsanity.com/paper/2302.08643/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction](https://mlsanity.com/paper/1610.00081/) (2016)
- [GRAND: Graph Neural Diffusion](https://mlsanity.com/paper/2106.10934/) (2021)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Spatial-Temporal Transformer Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2001.02908/) (2020)
- [Graph Neural Networks in Network Neuroscience](https://mlsanity.com/paper/2106.03535/) (2021)
- [Foreseeing Brain Graph Evolution Over Time Using Deep Adversarial Network Normalizer](https://mlsanity.com/paper/2009.11166/) (2020)
- [Fej'er-monotone hybrid steepest descent method for affinely constrained and composite convex minimization tasks](https://mlsanity.com/paper/1608.02500/) (2016)
- [Multiresolution Kernel Approximation for Gaussian Process Regression](https://mlsanity.com/paper/1708.02183/) (2017)
- [Residual Embedding Similarity-Based Network Selection for Predicting Brain Network Evolution Trajectory from a Single Observation](https://mlsanity.com/paper/2009.11110/) (2020)
- [The Incremental Multiresolution Matrix Factorization Algorithm](https://mlsanity.com/paper/1705.05804/) (2017)
- [An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works](https://mlsanity.com/paper/2105.14278/) (2021)
- [Parallel MMF: a Multiresolution Approach to Matrix Computation](https://mlsanity.com/paper/1507.04396/) (2015)

## Built on by (most cited first, 6 of 6)

- [Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's study](https://mlsanity.com/paper/2305.07731/) (2023)
- [TESGNN: Temporal Equivariant Scene Graph Neural Networks for Efficient and Robust Multi-View 3D Scene Understanding](https://mlsanity.com/paper/2411.10509/) (2024)
- [Multimodal Graph Learning for Modeling Emerging Pandemics with Big Data](https://mlsanity.com/paper/2310.14549/) (2023)
- [SAMSA: Efficient Transformer for Many Data Modalities](https://mlsanity.com/paper/2408.05391/) (2024)
- [Range-aware Positional Encoding via High-order Pretraining: Theory and Practice](https://mlsanity.com/paper/2409.19117/) (2024)
- [RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network](https://mlsanity.com/paper/2501.03221/) (2025)

## 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