{"id":13767951,"url":"https://github.com/SherylHYX/pytorch_geometric_signed_directed","last_synced_at":"2025-05-10T23:31:03.365Z","repository":{"id":43734048,"uuid":"422063657","full_name":"SherylHYX/pytorch_geometric_signed_directed","owner":"SherylHYX","description":"PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.","archived":false,"fork":false,"pushed_at":"2025-02-09T06:22:50.000Z","size":105683,"stargazers_count":137,"open_issues_count":1,"forks_count":18,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-04-12T22:03:58.007Z","etag":null,"topics":["deep-learning","directed-networks","gnn","graph-neural-netowrks","machine-learning","networks","python","pytorch","pytorch-geometric","signed-networks"],"latest_commit_sha":null,"homepage":"https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SherylHYX.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-10-28T04:26:49.000Z","updated_at":"2025-04-03T08:24:11.000Z","dependencies_parsed_at":"2023-02-17T17:16:06.538Z","dependency_job_id":"1bb9d593-e07c-42a5-9ff6-b17211d703a5","html_url":"https://github.com/SherylHYX/pytorch_geometric_signed_directed","commit_stats":{"total_commits":527,"total_committers":6,"mean_commits":87.83333333333333,"dds":"0.20872865275142316","last_synced_commit":"87fffa23183f3b8b71879948374b9a2a345d56fb"},"previous_names":[],"tags_count":39,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SherylHYX%2Fpytorch_geometric_signed_directed","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SherylHYX%2Fpytorch_geometric_signed_directed/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SherylHYX%2Fpytorch_geometric_signed_directed/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SherylHYX%2Fpytorch_geometric_signed_directed/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SherylHYX","download_url":"https://codeload.github.com/SherylHYX/pytorch_geometric_signed_directed/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253497296,"owners_count":21917683,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","directed-networks","gnn","graph-neural-netowrks","machine-learning","networks","python","pytorch","pytorch-geometric","signed-networks"],"created_at":"2024-08-03T16:01:14.628Z","updated_at":"2025-05-10T23:30:58.348Z","avatar_url":"https://github.com/SherylHYX.png","language":"Python","funding_links":[],"categories":["Graph Machine Learning","Pytorch \u0026 related libraries"],"sub_categories":["Others","Other libraries:"],"readme":"[![CI](https://github.com/SherylHYX/pytorch_geometric_signed_directed/actions/workflows/main.yml/badge.svg)](https://github.com/SherylHYX/pytorch_geometric_signed_directed/actions/workflows/main.yml)\n[![codecov](https://codecov.io/gh/SherylHYX/pytorch_geometric_signed_directed/branch/main/graph/badge.svg?token=441OFDGWRB)](https://codecov.io/gh/SherylHYX/pytorch_geometric_signed_directed)\n[![Documentation Status](https://readthedocs.org/projects/pytorch-geometric-signed-directed/badge/?version=latest)](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/?badge=latest)\n[![PyPI Version](https://badge.fury.io/py/torch-geometric-signed-directed.svg)](https://pypi.org/project/torch-geometric-signed-directed/)\n[![Contributing](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/SherylHYX/pytorch_geometric_signed_directed/blob/master/CONTRIBUTING.md)\n\n\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg width=\"90%\" src=\"https://raw.githubusercontent.com/SherylHYX/pytorch_geometric_signed_directed/master/docs/source/_static/img/text_logo.jpg?sanitize=true\" /\u003e\n\u003c/p\u003e\n\n**[Documentation](https://pytorch-geometric-signed-directed.readthedocs.io)** | **[Case Study](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/notes/case_study.html)** | **[Data Set Descriptions](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/notes/datasets.html)** | **[Installation](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/notes/installation.html)** | **[Data Structures](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/notes/introduction.html#data-structures)** | **[External Resources](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/notes/resources.html)** | **[Paper](https://arxiv.org/pdf/2202.10793.pdf)**\n\n-----------------------------------------------------\n\n*PyTorch Geometric Signed Directed* is a signed and directed extension library for [PyTorch Geometric](https://github.com/pyg-team/pytorch_geometric). It follows the package structure in [PyTorch Geometric Temporal](https://github.com/benedekrozemberczki/pytorch_geometric_temporal).\n\n\u003cp align=\"justify\"\u003eThe library consists of various signed and directed geometric deep learning, embedding, and clustering methods from a variety of published research papers and selected preprints. \n\nWe also provide detailed examples in the [examples](https://github.com/SherylHYX/pytorch_geometric_signed_directed/tree/main/examples) folder.\n\n\n--------------------------------------------------------------------------------\n\n**Citing**\n\n\nIf you find *PyTorch Geometric Signed Directed* useful in your research, please consider adding the following citation:\n\n```bibtex\n@inproceedings{he2024pytorch,\n  title={Pytorch Geometric Signed Directed: A software package on graph neural networks for signed and directed graphs},\n  author={He, Yixuan and Zhang, Xitong and Huang, Junjie and Rozemberczki, Benedek and Cucuringu, Mihai and Reinert, Gesine},\n  booktitle={Learning on Graphs Conference},\n  pages={12--1},\n  year={2024},\n  organization={PMLR}\n}\n```\n\n--------------------------------------------------------------------------------\n\n**Methods Included**\n\nIn detail, the following signed or directed graph neural networks, as well as related methods designed for signed or directed netwroks, were implemented.\n\n**Directed Unsigned Network Models and Layers**\n\n* **[MagNet_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.MagNet_node_classification.MagNet_node_classification)** from Zhang *et al.*: [MagNet: A Neural Network for Directed Graphs.](https://arxiv.org/pdf/2102.11391.pdf) (NeurIPS 2021)\n\n* **[DiGCL](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCL.DiGCL)** from Tong *et al.*: [Directed Graph Contrastive Learning.](https://proceedings.neurips.cc/paper/2021/file/a3048e47310d6efaa4b1eaf55227bc92-Paper.pdf) (NeurIPS 2021)\n\n* **[DiGCN_Inception_Block_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCN_node_classification.DiGCN_node_classification)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[DIGRAC_node_clustering](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DIGRAC_node_clustering.DIGRAC_node_clustering)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eExpand to see all methods implemented for directed networks...\u003c/b\u003e\u003c/summary\u003e\n\n* **[DGCN_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DGCN_node_classification.DGCN_node_classification)** from Tong *et al.*: [Directed Graph Convolutional Network.](https://arxiv.org/pdf/2004.13970.pdf) (ArXiv 2020)\n\n\n* **[DiGCN_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCN_node_classification.DiGCN_node_classification)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[MagNet_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.MagNet_link_prediction.MagNet_link_prediction)** from Zhang *et al.*: [MagNet: A Neural Network for Directed Graphs.](https://arxiv.org/pdf/2102.11391.pdf) (NeurIPS 2021)\n\n* **[DiGCN_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCN_link_prediction.DiGCN_link_prediction)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[DiGCN_Inception_Block_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCN_Inception_Block_link_prediction.DiGCN_Inception_Block_link_prediction)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[DGCN_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DGCN_link_prediction.DGCN_link_prediction)** from Tong *et al.*: [Directed Graph Convolutional Network.](https://arxiv.org/pdf/2004.13970.pdf) (ArXiv 2020)\n\n\n* **[DiGCN_Inception_Block](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCN_Inception_Block.DiGCN_InceptionBlock)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[DGCNConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DGCNConv.DGCNConv)** from Tong *et al.*: [Directed Graph Convolutional Network.](https://arxiv.org/pdf/2004.13970.pdf) (ArXiv 2020)\n\n* **[MagNetConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.MagNetConv.MagNetConv)** from Zhang *et al.*: [MagNet: A Neural Network for Directed Graphs.](https://arxiv.org/pdf/2102.11391.pdf) (NeurIPS 2021)\n\n* **[DiGCNConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DiGCNConv.DiGCNConv)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[DIMPA](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.directed.DIMPA.DIMPA)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n  \n\n\u003c/details\u003e\n\n**Signed (Directed) Network Models and Layers**\n\n* **[SSSNET_node_clustering](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SSSNET_node_clustering.SSSNET_node_clustering)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n* **[SDGNN](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SDGNN.SDGNN)** from Huang *et al.*: [SDGNN: Learning Node Representation for Signed Directed Networks](https://arxiv.org/pdf/2101.02390.pdf) (AAAI 2021)\n\n* **[SiGAT](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SiGAT.SiGAT)** from Huang *et al.*: [Signed Graph Attention Networks](https://arxiv.org/pdf/1906.10958.pdf) (ICANN 2019)\n\n\n* **[MSGNN_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.general.MSGNN.MSGNN_link_prediction)** from He *et al.*: [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian.](https://proceedings.mlr.press/v198/he22c.html) (LoG 2022)\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eExpand to see all methods implemented for signed networks...\u003c/b\u003e\u003c/summary\u003e\n\n* **[MSGNN_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.general.MSGNN.MSGNN_node_classification)** from He *et al.*: [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian.](https://proceedings.mlr.press/v198/he22c.html) (LoG 2022)\n\n* **[MSConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.general.MSConv.MSConv)** from He *et al.*: [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian.](https://proceedings.mlr.press/v198/he22c.html) (LoG 2022)\n\n* **[SSSNET_link_prediction](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SSSNET_link_prediction.SSSNET_link_prediction)** adapted from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n* **[SNEA](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SNEA.SNEA)** from Li *et al.*: [Learning Signed Network Embedding via Graph Attention](https://ojs.aaai.org/index.php/AAAI/article/view/5911) (AAAI 2020)\n\n* **[SGCN](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SGCN.SGCN)** from Derr *et al.*: [Signed Graph Convolutional Networks](https://arxiv.org/pdf/1808.06354.pdf) (ICDM 2018)\n\n* **[SNEAConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SNEAConv.SNEAConv)** from Li *et al.*: [Learning Signed Network Embedding via Graph Attention](https://ojs.aaai.org/index.php/AAAI/article/view/5911) (AAAI 2020)\n\n* **[SGCNConv](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SGCNConv.SGCNConv)** from Derr *et al.*: [Signed Graph Convolutional Network](https://arxiv.org/pdf/1808.06354.pdf) (ICDM 2018)\n\n\n* **[SIMPA](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.nn.signed.SIMPA.SIMPA)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n\n\u003c/details\u003e\n  \n\n\n**Network Generation Methods**\n\n* **[Signed Stochastic Block Model(SSBM)](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.SSBM.SSBM)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n* **[Polarized Signed Stochastic Block Model(POL-SSBM)](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.polarized_SSBM.polarized_SSBM)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n* **[Directed Stochastic Block Model(DSBM)](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.DSBM.DSBM)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n\n* **[Signed Directed Stochastic Block Model(SDSBM)](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.general.SDSBM.SDSBM)** from He *et al.*: [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian.](https://proceedings.mlr.press/v198/he22c.html) (LoG 2022)\n\n\n**Data Loaders and Classes**\n\n* **[load_signed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.load_signed_real_data.load_signed_real_data)** to load signed (directed) real-world data sets.\n\n* **[load_directed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.load_directed_real_data.load_directed_real_data)** to load directed unsigned real-world data sets.\n\n* **[SignedData](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.SignedData.SignedData)** Signed Data Class.\n\n* **[DirectedData](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.DirectedData.DirectedData)** Directed Data Class.\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eExpand to see all data loaders and related methods...\u003c/b\u003e\u003c/summary\u003e\n\n* **[SSSNET_signed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.SSSNET_real_data.SSSNET_real_data)** to load signed real-world data sets from the SSSNET paper.\n\n* **[SDGNN_signed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.SDGNN_real_data.SDGNN_real_data)** to load signed real-world data sets from the SDGNN paper.\n\n* **[MSGNN_signed_directed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.signed.MSGNN_real_data.MSGNN_real_data)** to load signed directed real-world data sets from the MSGNN paper.\n  \n* **[DIGRAC_directed_real_data](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.DIGRAC_real_data.DIGRAC_real_data)** to load directed real-world data sets from the DIGRAC paper.\n\n* **[Telegram](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.Telegram.Telegram)** to load the Telegram data set.\n\n* **[Cora_ml](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.citation.Cora_ml)** to load the Cora_ML data set.\n\n* **[Citeseer](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.citation.Citeseer)** to load the CiteSeer data set.\n\n* **[WikiCS](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.WikiCS.WikiCS)** to load the WikiCS data set.\n\n* **[WikipediaNetwork](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/data.html#torch_geometric_signed_directed.data.directed.WikipediaNetwork.WikipediaNetwork)** to load the WikipediaNetwork data set.\n  \n\u003c/details\u003e\n\n**Task-Specific Objectives and Evaluation Methods**\n\n* **[Probabilistic Balanced Normalized Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.signed.prob_balanced_normalized_loss.Prob_Balanced_Normalized_Loss)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n\n* **[Probabilistic Imbalance Objective](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.prob_imbalance_loss.Prob_Imbalance_Loss)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eExpand to see all task-specific objectives and evaluation methods...\u003c/b\u003e\u003c/summary\u003e\n\n* **[Probabilistic Balanced Ratio Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.signed.prob_balanced_ratio_loss.Prob_Balanced_Ratio_Loss)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n\n* **[Unhappy Ratio](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.signed.unhappy_ratio.Unhappy_Ratio)** from He *et al.*: [SSSNET: Semi-Supervised Signed Network Clustering](https://arxiv.org/pdf/2110.06623.pdf) (SDM 2022)\n  \n* **[link_sign_prediction_logistic_function](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.signed.link_sign_prediction_logistic_function.link_sign_prediction_logistic_function)** for signed networks' link sign prediction task.\n\n* **[link_sign_direction_prediction_logistic_function](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.link_sign_direction_prediction_logistic_function.link_sign_prediction_logistic_function)** for signed directed networks' link prediction task.\n\n* **[triplet_loss_node_classification](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.triplet_loss.triplet_loss_node_classification)** for triplet loss in the node classification task.\n\n* **[Sign_Triangle_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Sign_Triangle_Loss)** from Huang *et al.*: [SDGNN: Learning Node Representation for Signed Directed Networks](https://arxiv.org/pdf/2101.02390.pdf) (AAAI 2021)\n\n* **[Sign_Direction_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Sign_Direction_Loss)** from Huang *et al.*: [SDGNN: Learning Node Representation for Signed Directed Networks](https://arxiv.org/pdf/2101.02390.pdf) (AAAI 2021)\n\n* **[Sign_Product_Entropy_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Sign_Product_Entropy_Loss)** from Huang *et al.*: [SDGNN: Learning Node Representation for Signed Directed Networks](https://arxiv.org/pdf/2101.02390.pdf) (AAAI 2021)\n\n* **[Link_Sign_Product_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Link_Sign_Product_Loss)** from Huang *et al.*: [Signed Graph Attention Networks](https://arxiv.org/pdf/1906.10958.pdf) (ICANN 2019)\n\n* **[Link_Sign_Entropy_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Link_Sign_Entropy_Loss)** from Derr *et al.*: [Signed Graph Convolutional Network](https://arxiv.org/pdf/1808.06354.pdf) (ICDM 2018)\n\n* **[Sign_Structure_Loss](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/model.html#torch_geometric_signed_directed.utils.signed.link_sign_loss.Sign_Structure_Loss)** \n\u003c/details\u003e\n\n**Utilities and Preprocessing Methods**\n\n* **[node_class_split](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.node_split.node_class_split)** to split nodes into training set etc..\n\n* **[link_class_split](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.link_split.link_class_split)** to split edges into training set etc..\n\n* **[get_magnetic_Laplacian](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.get_magnetic_Laplacian.get_magnetic_Laplacian)** from from Zhang *et al.*: [MagNet: A Neural Network for Directed Graphs.](https://arxiv.org/pdf/2102.11391.pdf) (NeurIPS 2021)\n\n* **[get_magnetic_signed_Laplacian](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.get_magnetic_signed_Laplacian.get_magnetic_signed_Laplacian)** from He *et al.*: [MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian.](https://proceedings.mlr.press/v198/he22c.html) (LoG 2022)\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eExpand to see all utilities and preprocessing methods...\u003c/b\u003e\u003c/summary\u003e\n\n* **[get_appr_directed_adj](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.get_adjs_DiGCN.get_appr_directed_adj)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n  \n* **[meta_graph_generation](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.meta_graph_generation.meta_graph_generation)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (ArXiv 2021)\n\n* **[extract_network](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.extract_network.extract_network)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n\n* **[directed_features_in_out](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.features_in_out.directed_features_in_out)** from Tong *et al.*: [Directed Graph Convolutional Network.](https://arxiv.org/pdf/2004.13970.pdf) (ArXiv 2020)\n\n* **[get_second_directed_adj](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.get_adjs_DiGCN.get_second_directed_adj)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n* **[cal_fast_appr](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.directed.get_adjs_DiGCN.cal_fast_appr)** from Tong *et al.*: [Digraph Inception Convolutional Networks.](https://papers.nips.cc/paper/2020/file/cffb6e2288a630c2a787a64ccc67097c-Paper.pdf) (NeurIPS 2020)\n\n\n* **[scipy_sparse_to_torch_sparse](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.general.scipy_sparse_to_torch_sparse.scipy_sparse_to_torch_sparse)** from He *et al.*: [DIGRAC: Digraph Clustering Based on Flow Imbalance.](https://proceedings.mlr.press/v198/he22b.html) (LoG 2022)\n\n\n* **[create spectral features](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/modules/utils.html#torch_geometric_signed_directed.utils.signed.create_spectral_features.create_spectral_features)**\n  \n\u003c/details\u003e\n\n--------------------------------------------------------------------------------\n\nHead over to our [documentation](https://pytorch-geometric-signed-directed.readthedocs.io/en/latest/) to find out more!\nIf you notice anything unexpected, please open an [issue](https://github.com/SherylHYX/pytorch_geometric_signed_directed/issues). If you are missing a specific method, feel free to open a [feature request](https://github.com/SherylHYX/pytorch_geometric_signed_directed/issues).\n\n\n--------------------------------------------------------------------------------\n\n**Installation**\n\nBinaries are provided for Python version \u003e= 3.7 and NetworkX version \u003c 2.7.\n\nAfter installing [PyTorch](https://pytorch.org/get-started/locally/) and [PyG](https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html), simply run\n\n```sh\npip install torch-geometric-signed-directed\n```\n--------------------------------------------------------------------------------\n\n**Running tests**\n\n```\n$ python setup.py test\n```\n--------------------------------------------------------------------------------\n\n**License**\n\n- [MIT License](https://github.com/SherylHYX/pytorch_geometric_signed_directed/blob/master/LICENSE)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSherylHYX%2Fpytorch_geometric_signed_directed","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FSherylHYX%2Fpytorch_geometric_signed_directed","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FSherylHYX%2Fpytorch_geometric_signed_directed/lists"}