Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abate, Carlo, Marisca, Ivan, Bianchi, Filippo Maria
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910148117659648
author Abate, Carlo
Marisca, Ivan
Bianchi, Filippo Maria
author_facet Abate, Carlo
Marisca, Ivan
Bianchi, Filippo Maria
contents Torch Geometric Pool (tgp) is a pooling library built on top of PyTorch Geometric. Graph pooling methods differ in how they assign nodes to supernodes, how they handle batches, what they return after pooling, and whether they expose auxiliary losses. These differences make it hard to compare methods or reuse the same model code across them. tgp addresses this problem with a common software interface based on the Select-Reduce-Connect-Lift (SRCL) decomposition. The library provides 20 hierarchical poolers, standardized output objects, standalone readout modules, support for dense poolers in batched and unbatched mode, and workflows for caching and pre-coarsening. It is released under the MIT license on GitHub and PyPI, with comprehensive documentation, tutorials, and examples.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12642
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks
Abate, Carlo
Marisca, Ivan
Bianchi, Filippo Maria
Machine Learning
Torch Geometric Pool (tgp) is a pooling library built on top of PyTorch Geometric. Graph pooling methods differ in how they assign nodes to supernodes, how they handle batches, what they return after pooling, and whether they expose auxiliary losses. These differences make it hard to compare methods or reuse the same model code across them. tgp addresses this problem with a common software interface based on the Select-Reduce-Connect-Lift (SRCL) decomposition. The library provides 20 hierarchical poolers, standardized output objects, standalone readout modules, support for dense poolers in batched and unbatched mode, and workflows for caching and pre-coarsening. It is released under the MIT license on GitHub and PyPI, with comprehensive documentation, tutorials, and examples.
title Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2512.12642