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

TL;DR

PyTorch Geometric Temporal is a comprehensive deep learning framework that enables neural spatiotemporal signal processing, making advanced geometric deep learning techniques accessible for real-world applications and large datasets.

Contribution

The paper introduces PyTorch Geometric Temporal, a unified, easy-to-use library integrating state-of-the-art models for neural spatiotemporal signal processing within the PyTorch ecosystem.

Findings

Demonstrates superior predictive performance on epidemiological, demand, and web-traffic datasets.

Shows the framework's scalability to web-scale datasets with rich temporal and spatial features.

Provides a tutorial and benchmark datasets for practical adoption.

Abstract

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.