Community News and Events


Accelerating PyG on IPUs: Unleash the Power of Graph Neural Networks

Graphcore Intelligence Processing Units have demonstrated standout performance running a wide range of GNNs. Find out why GNNs work so well on IPUs.

Press articleDetails

Accelerating Graph Learning with HGT

The HGT uses attention over features of each node and edge type in a heterogeneous graph instead of over the tokens in a sentence or pixels in an image/video as is done with traditional transformers.

Press articleDetails

PyG 2.2 Release

We are excited to announce the release of PyG 2.2 🎉🎉🎉 PyG 2.2 is the culmination of work from 78 contributors who have worked on features and bug-fixes for a total of over 320 commits since torch-geometric==2.1.0.

Press articleDetails

GraphGym & PyG Integration

GraphGym is a platform for designing and evaluating Graph Neural Networks (GNNs), as originally proposed in the “Design Space for Graph Neural Networks” paper. We now officially support GraphGym as part of of PyG.

Press articleDetails

PyG 2.0 Release

PyG (PyTorch Geometric) has been moved from the personal account rusty1s to its own organization account pyg-team to emphasize the ongoing collaboration between TU Dortmund University, Stanford University and many great external contributors. With this, we are releasing PyG 2.0, a new major release that brings sophisticated heterogeneous graph support, GraphGym and many other exciting features to PyG.

Press articleDetails

Contact us at