Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Fey, Matthias, Sunil, Jinu, Nitta, Akihiro, Puri, Rishi, Shah, Manan, Stojanovič, Blaž, Bendias, Ramona, Barghi, Alexandria, Kocijan, Vid, Zhang, Zecheng, He, Xinwei, Lenssen, Jan Eric, Leskovec, Jure
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414877928