PyG 2.0: Scalable Learning on Real World Graphs
This is an incremental update to a widely used framework for researchers and practitioners in graph learning.
The paper presents PyG 2.0, an updated framework for Graph Neural Networks that tackles scalability and real-world application challenges by introducing support for heterogeneous and temporal graphs, scalable stores, and optimizations, enabling efficient large-scale graph learning.
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.