PyG 2.0: Scalable Learning on Real World Graphs

Matthias Fey, Jinu Sunil, Akihiro Nitta, Rishi Puri, Manan Shah, Blaž Stojanovič, Ramona Bendias, Alexandria Barghi, Vid Kocijan, Zecheng Zhang, Xinwei He, Jan Eric Lenssen, Jure Leskovec

Keywords: temporal graph learning, data mining

TL;DR: We present PyG 2.0, a comprehensive update to PyG (PyTorch Geometric) that introduces substantial improvements in scalability and real-world application capabilities.

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, 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.

Format: Long paper, up to 8 pages.

Submission Number: 13