Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks
By: Filippo Maria Bianchi, Carlo Abate, Ivan Marisca
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.
Similar Papers
Geometry-Aware Edge Pooling for Graph Neural Networks
Machine Learning (CS)
Keeps important connections when shrinking computer data.
Rhomboid Tiling for Geometric Graph Deep Learning
Machine Learning (CS)
Finds hidden patterns in complex shapes.
SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
Machine Learning (Stat)
Makes computer graphs smaller and faster.