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

Yixuan He, Xitong Zhang, Junjie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert
Proceedings of the Second Learning on Graphs Conference, PMLR 231:12:1-12:27, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v231-he24a, title = {PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs}, author = {He, Yixuan and Zhang, Xitong and Huang, Junjie and Rozemberczki, Benedek and Cucuringu, Mihai and Reinert, Gesine}, booktitle = {Proceedings of the Second Learning on Graphs Conference}, pages = {12:1--12:27}, year = {2024}, editor = {Villar, Soledad and Chamberlain, Benjamin}, volume = {231}, series = {Proceedings of Machine Learning Research}, month = {27--30 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v231/he24a/he24a.pdf}, url = {https://proceedings.mlr.press/v231/he24a.html}, 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.} }
Endnote
%0 Conference Paper %T PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs %A Yixuan He %A Xitong Zhang %A Junjie Huang %A Benedek Rozemberczki %A Mihai Cucuringu %A Gesine Reinert %B Proceedings of the Second Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2024 %E Soledad Villar %E Benjamin Chamberlain %F pmlr-v231-he24a %I PMLR %P 12:1--12:27 %U https://proceedings.mlr.press/v231/he24a.html %V 231 %X 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.
APA
He, Y., Zhang, X., Huang, J., Rozemberczki, B., Cucuringu, M. & Reinert, G.. (2024). PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs. Proceedings of the Second Learning on Graphs Conference, in Proceedings of Machine Learning Research 231:12:1-12:27 Available from https://proceedings.mlr.press/v231/he24a.html.

Related Material