pytorch_geometric_temporal
A PyTorch library for spatiotemporal signal processing with dynamic and temporal graph neural networks.
What is pytorch_geometric_temporal?
PyTorch Geometric Temporal is a temporal extension library for PyTorch Geometric designed for spatiotemporal signal processing with neural machine learning models. It provides a comprehensive suite of tools for handling dynamic and temporal graphs, enabling research and applications in domains like traffic forecasting, epidemiological modeling, and energy production. The library implements various dynamic and temporal geometric deep learning, embedding, and spatio-temporal regression methods from published research papers.
Researchers and machine learning engineers working on spatiotemporal data analysis, particularly those focused on dynamic graph neural networks for applications such as traffic prediction, epidemiological forecasting, and energy production modeling. It is also suitable for developers needing scalable, GPU-accelerated temporal graph processing with integration into PyTorch ecosystems.
Developers choose PyTorch Geometric Temporal because it offers a unified, easy-to-use library specifically for temporal graph neural networks, bridging cutting-edge research with practical applications. Its unique selling points include built-in GPU support, memory-efficient index-batching for scalability, seamless integration with PyTorch Lightning for distributed training, and a comprehensive collection of benchmark datasets and pre-implemented models from recent papers.
Overview
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
Use Cases
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
