Fast Temporal Wavelet Graph Neural Networks
This work addresses forecasting challenges in domains like traffic and brain networks, offering an incremental improvement in efficiency for existing graph neural network approaches.
The paper tackles spatio-temporal forecasting in neuroscience and transportation by proposing FTWGNN, a time- and memory-efficient model that uses wavelet theory and multiresolution analysis to handle graph-structured timeseries data. Experimental results on traffic and ECoG datasets show it is competitive with state-of-the-art methods while maintaining low computational costs.
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