Fast Graph Representation Learning with PyTorch Geometric

Abstract

We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.

ICLR 2019 (RLGM Workshop)

References in corpus (3)

• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks

Cited by in corpus (8)

• Self-Attention Graph Pooling
• Edge Contraction Pooling for Graph Neural Networks
• Spectral-based Graph Convolutional Network for Directed Graphs
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
• Graph Neural Network for Interpreting Task-fMRI Biomarkers
• Discriminative structural graph classification
• On Graph Classification Networks, Datasets and Baselines
• Are Graph Neural Networks Miscalibrated?