PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models
This framework addresses the need for accessible temporal geometric deep learning tools for researchers and machine learning practitioners, though it is incremental as it builds on existing PyTorch libraries.
The authors introduced PyTorch Geometric Temporal, a deep learning framework for spatiotemporal signal processing, which provides a unified and easy-to-use toolkit for researchers and practitioners, demonstrating its predictive performance on real-world problems like epidemiological forecasting and ridehail demand prediction.
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 of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easy-to-use framework. PyTorch Geometric Temporal was created with foundations on existing libraries in the PyTorch eco-system, streamlined neural network layer definitions, temporal snapshot generators for batching, and integrated benchmark datasets. These features are illustrated with a tutorial-like case study. Experiments demonstrate the predictive performance of the models implemented in the library on real world problems such as epidemiological forecasting, ridehail demand prediction and web-traffic management. Our sensitivity analysis of runtime shows that the framework can potentially operate on web-scale datasets with rich temporal features and spatial structure.