The new paper “Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks” by Filippo Maria Bianchi, Carlo Abate, and Ivan Marisca is out!

We present Torch Geometric Pool (TGP), a PyTorch library that implements a wide variety of graph pooling methods for GNNs. TGP is designed with an easy-to-use API, enabling seamless integration with existing PyTorch Geometric codebases. The library includes implementations of state-of-the-art pooling techniques, along with comprehensive documentation and examples to facilitate adoption by the research community.

The preprint is available on Arxiv.