Pytorch geometric temporal: Spatiotemporal signal processing with neural machine learning models
We present PyTorch Geometric Temporal, a deep learning framework combining state-of-the-
art machine learning algorithms for neural spatiotemporal signal processing. The main goal …
art machine learning algorithms for neural spatiotemporal signal processing. The main goal …
Multiobjective evolution of the explainable fuzzy rough neural network with gene expression programming
B Cao, J Zhao, X Liu, J Arabas… - … on Fuzzy Systems, 2022 - ieeexplore.ieee.org
The fuzzy logic-based neural network usually forms fuzzy rules via multiplying the input
membership degrees, which lacks expressiveness and flexibility. In this article, a novel …
membership degrees, which lacks expressiveness and flexibility. In this article, a novel …
Multi-scale temporal features extraction based graph convolutional network with attention for multivariate time series prediction
Y Chen, F Ding, L Zhai - Expert Systems with Applications, 2022 - Elsevier
Modeling for multivariate time series have always been a meaningful subject. Multivariate
time series forecasting is a fundamental problem attracting many researchers in various …
time series forecasting is a fundamental problem attracting many researchers in various …
DynaGraph: dynamic graph neural networks at scale
In this paper, we present DynaGraph, a system that supports dynamic Graph Neural
Networks (GNNs) efficiently. Based on the observation that existing proposals for dynamic …
Networks (GNNs) efficiently. Based on the observation that existing proposals for dynamic …
Temporal dynamics-aware adversarial attacks on discrete-time dynamic graph models
Real-world graphs such as social networks, communication networks, and rating networks
are constantly evolving over time. Many deep learning architectures have been developed …
are constantly evolving over time. Many deep learning architectures have been developed …
Temporal graph neural networks for irregular data
J Oskarsson, P Sidén… - … Conference on Artificial …, 2023 - proceedings.mlr.press
This paper proposes a temporal graph neural network model for forecasting of graph-
structured irregularly observed time series. Our TGNN4I model is designed to handle both …
structured irregularly observed time series. Our TGNN4I model is designed to handle both …
Time-series transformer generative adversarial networks
P Srinivasan, WJ Knottenbelt - arXiv preprint arXiv:2205.11164, 2022 - arxiv.org
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 (eg GDPR). We …
available and in others, data is protected by privacy enforcing regulations (eg GDPR). We …
Non-separable spatio-temporal graph kernels via SPDEs
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 …
learning on graphs. However, the lack of justified graph kernels for spatio-temporal …
Think: Temporal hypergraph hyperbolic network
Network-based time series forecasting is a challenging task as it involves complex
geometric properties, higher-order relations, and scale-free characteristics. Previous work …
geometric properties, higher-order relations, and scale-free characteristics. Previous work …
A Survey of Transformer Enabled Time Series Synthesis
Generative AI has received much attention in the image and language domains, with the
transformer neural network continuing to dominate the state of the art. Application of these …
transformer neural network continuing to dominate the state of the art. Application of these …