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

Rózemberczki, Benedek; Scherer, Paul; Kiss, Oliver; Sarkar, Rik; Ferenci, Tamás

doi:10.48550/arxiv.2102.08100

Cited by 9 publications

(13 citation statements)

References 15 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluated our methods on a data set of chickenpox cases in Hungary (Rozemberczki et al, 2021b We observed similar results to the COVID-19 case: GP approaches outperformed the GNN approach, SHEK has shown comparable performance with separable kernel on the extrapolation task with more stable performance across the validation rounds. The separable kernel has shown better performance on the interpolation task than SHEK (DM-test, p = 0.05).…”

Section: Hungary Chickenpox Data Setmentioning

confidence: 69%

Non-separable Spatio-temporal Graph Kernels via SPDEs

Nikitin¹,

John²,

Solin³

et al. 2021

Preprint

View full text Add to dashboard Cite

Gaussian processes (GPs) provide a principled and direct approach for inference and learning on graphs. However, the lack of justified graph kernels for spatio-temporal modelling has held back their use in graph problems. We leverage an explicit link between stochastic partial differential equations (SPDEs) and GPs on graphs, and derive nonseparable spatio-temporal graph kernels that capture interaction across space and time. We formulate the graph kernels for the stochastic heat equation and wave equation. We show that by providing novel tools for spatiotemporal GP modelling on graphs, we outperform pre-existing graph kernels in real-world applications that feature diffusion, oscillation, and other complicated interactions.

show abstract

Section: Hungary Chickenpox Data Setmentioning

confidence: 69%

Non-separable Spatio-temporal Graph Kernels via SPDEs

Nikitin¹,

John²,

Solin³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…4. Chickenpox The UCI Hungarian Chickenpox Cases dataset [40,16] consists of records of chickenpox cases weekly in 20 counties in Hungary. This dataset represents a realistic situation where generative models be trained on small amounts of data and then generate synthetic samples to train other models.…”

Section: Energymentioning

confidence: 99%

Time-series Transformer Generative Adversarial Networks

Srinivasan¹,

Knottenbelt²

2022

Preprint

View full text Add to dashboard Cite

Many real-world tasks are plagued by limitations on data: in some instances very little data is available and in others, data is protected by privacy enforcing regulations (e.g. GDPR). We consider limitations posed specifically on time-series data and present a model that can generate synthetic time-series which can be used in place of real data. A model that generates synthetic time-series data has two objectives: 1) to capture the stepwise conditional distribution of real sequences, and 2) to faithfully model the joint distribution of entire real sequences. Autoregressive models trained via maximum likelihood estimation can be used in a system where previous predictions are fed back in and used to predict future ones; in such models, errors can accrue over time. Furthermore, a plausible initial value is required making MLE based models not really generative. Many downstream tasks learn to model conditional distributions of the time-series, hence, synthetic data drawn from a generative model must satisfy 1) in addition to performing 2). We present TsT-GAN, a framework that capitalises on the Transformer architecture to satisfy the desiderata and compare its performance against five state-of-the-art models on five datasets and show that TsT-GAN achieves higher predictive performance on all datasets.Preprint. Under review.

show abstract

“…The chickenpox dataset [11] includes weekly chickenpox cases from 20 cities in Hungary. We performed predictions for Budapest.…”

Section: Alp-local For Predicting Chickenpox Casesmentioning

confidence: 99%

Improving Laplacian Pyramids Regression with Localization in Frequency and Time

Rabin¹,

Hen²,

Fernandez³

2022

ESANN 2022 Proceedings

View full text Add to dashboard Cite

Auto-Adaptive Laplacian Pyramids (ALP) is an iterative kernel-based regression model. It constructs a multi-scale representation of the train data, where the multi-scale modes are average residuals. In this work, we propose two extensions of the model. The first is a hybrid approach that combines ALP with Empirical Mode Decomposition to provide localization in the frequency domain. The second modifies ALP to fit datasets with non-uniform noise, which is achieved by computing the optimal stopping criterion in a point-dependent manner. Experimental results demonstrate these models for solar energy prediction and for forecasting epidemiology infections.

show abstract

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

Cited by 9 publications

References 15 publications

Non-separable Spatio-temporal Graph Kernels via SPDEs

Non-separable Spatio-temporal Graph Kernels via SPDEs

Time-series Transformer Generative Adversarial Networks

Improving Laplacian Pyramids Regression with Localization in Frequency and Time

Contact Info

Product

Resources

About