PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs
This provides a software solution for researchers and practitioners working with signed and directed networks, such as in social networks or correlation analysis, but it is incremental as it builds on existing PyTorch Geometric libraries.
The authors tackled the lack of unified software for graph neural networks on signed and directed networks by developing PyTorch Geometric Signed Directed (PyGSD), a package that includes models, data, and evaluation metrics, with experiments providing insights for method selection.
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.