PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs

TL;DR

PyTorch Geometric Signed Directed (PyGSD) is an open-source software package that provides GNN models and tools specifically designed for signed and directed networks, addressing a gap in existing graph neural network software.

Contribution

The paper introduces PyGSD, a comprehensive, easy-to-use software package for GNNs on signed and directed graphs, with evaluation and insights for task-specific model selection.

Findings

Provides a unified framework for signed and directed GNNs

Includes synthetic and real-world datasets for evaluation

Offers detailed documentation and open-source code

Abstract

Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks. In this paper, we present PyTorch Geometric Signed Directed (PyGSD), a software package which fills this gap. Along the way, we evaluate the implemented methods with experiments with a view to providing insights into which method to choose for a given task. The deep learning framework consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions for signed and directed networks. As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks. The GitHub repository of the library is https://github.com/SherylHYX/pytorch_geometric_signed_directed.