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

• URL: http://arxiv.org/abs/2512.12642v1
• Date: Sun, 14 Dec 2025 11:15:09 GMT
• Title: Torch Geometric Pool: the Pytorch library for pooling in Graph Neural Networks
• Authors: Filippo Maria Bianchi, Carlo Abate, Ivan Marisca,
• Abstract summary: We introduce Torch Geometric Pool (tgp), a library for hierarchical pooling in Graph Neural Networks.<n>Built upon Pytorch Geometric, tgp provides a wide variety of pooling operators, unified under a consistent API and a modular design.
• Score: 17.28885611561219
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks [3.634532073343371]
  This paper introduces SpaPool, a novel pooling method for a graph neural network.<n>It combines the strengths of both dense and sparse techniques for a graph neural network.<n>It aims to maintain the structural integrity of the graph while reducing its size efficiently.
  arXiv  Detail & Related papers  (2025-09-15T08:16:40Z)
• Geometry-Aware Edge Pooling for Graph Neural Networks [23.216349399814643]
  Graph Neural Networks (GNNs) have shown significant success for graph-based tasks.<n>Motivated by the prevalence of large datasets in real-world applications, pooling layers are crucial components of GNNs.<n>We propose novel graph pooling layers for structure-aware pooling via edge collapses.
  arXiv  Detail & Related papers  (2025-06-13T12:01:46Z)
• torchgfn: A PyTorch GFlowNet library [44.94532429787822]
  We present torchgfn, a PyTorch library that aims to address this need.<n>Its core contribution is a modular and decoupled architecture which treats environments, neural network modules, and training objectives as interchangeable components.<n>This provides users with a simple yet powerful API to facilitate rapid prototyping and novel research.
  arXiv  Detail & Related papers  (2023-05-24T00:20:59Z)
• Higher-order Clustering and Pooling for Graph Neural Networks [77.47617360812023]
  Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks. HoscPool is a clustering-based graph pooling operator that captures higher-order information hierarchically. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure.
  arXiv  Detail & Related papers  (2022-09-02T09:17:10Z)
• AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling [82.08631594071656]
  Pooling layers are essential building blocks of Convolutional Neural Networks (CNNs) We propose an adaptive and exponentially weighted pooling method named adaPool. We demonstrate how adaPool improves the preservation of detail through a range of tasks including image and video classification and object detection.
  arXiv  Detail & Related papers  (2021-11-01T08:50:37Z)
• Efficient Graph Deep Learning in TensorFlow with tf_geometric [53.237754811019464]
  We introduce tf_geometric, an efficient and friendly library for graph deep learning. tf_geometric provides kernel libraries for building Graph Neural Networks (GNNs) as well as implementations of popular GNNs. The kernel libraries consist of infrastructures for building efficient GNNs, including graph data structures, graph map-reduce framework, graph mini-batch strategy, etc.
  arXiv  Detail & Related papers  (2021-01-27T17:16:36Z)
• TorchRadon: Fast Differentiable Routines for Computed Tomography [0.0]
  The TorchRadon library is designed to help researchers working on CT problems to combine deep learning and model-based approaches. Compared to the existing Astra Toolbox, TorchRadon is up to 125 faster. Because of its speed and GPU support, TorchRadon can also be effectively used as a fast backend for the implementation of iterative algorithms.
  arXiv  Detail & Related papers  (2020-09-29T09:20:22Z)
• Captum: A unified and generic model interpretability library for PyTorch [49.72749684393332]
  We introduce a novel, unified, open-source model interpretability library for PyTorch. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms. It can be used for both classification and non-classification models.
  arXiv  Detail & Related papers  (2020-09-16T18:57:57Z)
• Graph Neural Networks in TensorFlow and Keras with Spektral [18.493394650508044]
  Spektral is an open-source Python library for building graph neural networks. It implements a large set of methods for deep learning on graphs, including message-passing and pooling operators. It is suitable for absolute beginners and expert deep learning practitioners alike.
  arXiv  Detail & Related papers  (2020-06-22T10:56:22Z)
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing [161.7521770950933]
  We introduce strip pooling, which considers a long but narrow kernel, i.e., 1xN or Nx1. We compare the performance of the proposed strip pooling and conventional spatial pooling techniques. Both novel pooling-based designs are lightweight and can serve as an efficient plug-and-play module in existing scene parsing networks.
  arXiv  Detail & Related papers  (2020-03-30T10:40:11Z)
• Torch-Struct: Deep Structured Prediction Library [138.5262350501951]
  We introduce Torch-Struct, a library for structured prediction. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API.
  arXiv  Detail & Related papers  (2020-02-03T16:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.