PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models

Rózemberczki, Benedek; Scherer, Paul; He, Yixuan; Panagopoulos, George; Riedel, Alexander; Astefanoaei, Maria; Kiss, Oliver; Béres, Ferenc; López, Guzmán; Collignon, Nicolas; Sarkar, Rik

doi:10.1145/3459637.3482014

Cited by 97 publications

(48 citation statements)

References 35 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Wikipedia-Math-Daily dataset is part of the Wikipedia-Math dataset [25]. The Wikipedia-Math dataset contains a weighted link network among 1068 Wikipedia pages about Mathematics topics.…”

Section: ) the Wikipedia-math-daily Datasetmentioning

confidence: 99%

Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs

Zhao,

Ayanoglu

2022

Preprint

View full text Add to dashboard Cite

This paper discusses a special kind of a simple yet possibly powerful algorithm, called single-kernel Gradraker (SKG), which is an adaptive learning method predicting unknown nodal values in a network using known nodal values and the network structure. We aim to find out how to configure the special kind of the model in applying the algorithm. To be more specific, we focus on SKG with a Gaussian kernel and specify how to find a suitable variance for the kernel. To do so, we introduce two variables with which we are able to set up requirements on the variance of the Gaussian kernel to achieve (near-) optimal performance and can better understand how SKG works.Our contribution is that we introduce two variables as analysis tools, illustrate how predictions will be affected under different Gaussian kernels, and provide an algorithm finding a suitable Gaussian kernel for SKG with knowledge about the training network. Simulation results on real datasets are provided.

show abstract

Section: ) the Wikipedia-math-daily Datasetmentioning

confidence: 99%

Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs

Zhao,

Ayanoglu

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A summary of the major operations involved in ChebNet, GCN, and diffusion graph convolution is shown in Figure S1 in Supporting Information S1. These modules are typically implemented as layers in modern graph learning libraries and may be interlaced with other ML modules (e.g., Rozemberczki et al, 2021). Unlike the deep CNN, the architectures of most GNNs are relatively shallow, because a node's neighborhood can grow rapidly after just a few layers.…”

Section: Spatial Graph Convolutionmentioning

confidence: 99%

Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks

Sun

Jiang

Mudunuru

2021

Water Resources Research

View full text Add to dashboard Cite

Streamflow is the spatial integral of basin input, storage, and runoff processes. It provides a direct measure of water availability and the impact of climate change and human activities at the basin level (Milly et al., 2005;Hannah et al., 2011). Quantifying streamflow regimes and their spatiotemporal similarity can reveal valuable insights on the controlling hydroclimatic, geomorphic, and ecological processes, improving water resources planning and management (Coopersmith et al., 2012;Ghotbi et al., 2020). Current practices in hydrological modeling are either depth driven or breadth driven (Gupta et al., 2014). The former category seeks to improve process understanding at the catchment scale, aiming to provide detailed and physically realistic catchment models for a specific basin through in situ sampling and long-term monitoring (Blöschl et al., 2019); while the latter focuses on the development and application of hydrological models at the continental and global scales, seeking to provide a global assessment of water scarcity (

show abstract

“…We tested the predictive performance of recurrent graph neural networks on county level chickenpox time series forecasting. Using the PyTorch Geometric Temporal [5,16,18] implementation of the models we trained on the standardized chickenpox time series and predicted it for a fixed number of weeks ahead. The input graph describes the undirected direct adjacency relations of the counties.…”

Section: Neural Benchmarksmentioning

confidence: 99%

Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks

Rózemberczki¹,

Scherer²,

Kiss³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recurrent graph convolutional neural networks are highly effective machine learning techniques for spatiotemporal signal processing. Newly proposed graph neural network architectures are repetitively evaluated on standard tasks such as traffic or weather forecasting. In this paper, we propose the Chickenpox Cases in Hungary dataset as a new dataset for comparing graph neural network architectures. Our time series analysis and forecasting experiments demonstrate that the Chickenpox Cases in Hungary dataset is adequate for comparing the predictive performance and forecasting capabilities of novel recurrent graph neural network architectures.

show abstract

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models

Cited by 97 publications

References 35 publications

Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs

Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs

Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks

Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks

Contact Info

Product

Resources

About