PyG 2.0: Scalable Learning on Real World Graphs

TL;DR

PyG 2.0 is a major update to the PyTorch Geometric framework, significantly enhancing scalability, supporting heterogeneous and temporal graphs, and enabling efficient large-scale graph learning for real-world applications.

Contribution

The paper introduces PyG 2.0 with new architecture features, scalability improvements, and support for diverse graph types, advancing the framework's capabilities for large-scale graph learning.

Findings

Enhanced scalability for large graphs

Support for heterogeneous and temporal graphs

Improved performance in real-world applications

Abstract

PyG (PyTorch Geometric) has evolved significantly since its initial release, establishing itself as a leading framework for Graph Neural Networks. In this paper, we present Pyg 2.0 (and its subsequent minor versions), a comprehensive update that introduces substantial improvements in scalability and real-world application capabilities. We detail the framework's enhanced architecture, including support for heterogeneous and temporal graphs, scalable feature/graph stores, and various optimizations, enabling researchers and practitioners to tackle large-scale graph learning problems efficiently. Over the recent years, PyG has been supporting graph learning in a large variety of application areas, which we will summarize, while providing a deep dive into the important areas of relational deep learning and large language modeling.