Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks
This provides a tool for researchers and practitioners in graph machine learning to enable fast prototyping of pooling methods, though it is incremental as it builds on existing frameworks.
The authors introduced Torch Geometric Pool (tgp), a library for hierarchical pooling in Graph Neural Networks built on PyTorch Geometric, offering various pooling operators with a consistent API and modular design, and benchmarked it to show that optimal pooling operator choice depends on tasks and data.
We introduce Torch Geometric Pool (tgp), a library for hierarchical pooling in Graph Neural Networks. Built upon Pytorch Geometric, Torch Geometric Pool (tgp) provides a wide variety of pooling operators, unified under a consistent API and a modular design. The library emphasizes usability and extensibility, and includes features like precomputed pooling, which significantly accelerate training for a class of operators. In this paper, we present tgp's structure and present an extensive benchmark. The latter showcases the library's features and systematically compares the performance of the implemented graph-pooling methods in different downstream tasks. The results, showing that the choice of the optimal pooling operator depends on tasks and data at hand, support the need for a library that enables fast prototyping.