Data

Tools

Indexes

Applications

Experiments

Open Source Science

torch-geometric-signed-directed

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

https://github.com/sherylhyx/pytorch_geometric_signed_directed

Science Score: 64.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ✓
    Committers with academic emails
    2 of 5 committers (40.0%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (14.0%) to scientific vocabulary

Keywords

deep-learning directed-networks gnn graph-neural-netowrks machine-learning networks python pytorch pytorch-geometric signed-networks
Last synced: 6 months ago · JSON representation ·

Repository

PyTorch Geometric Signed Directed is a signed/directed graph neural network extension library for PyTorch Geometric. The paper is accepted by LoG 2023.

Basic Info
Statistics
  • Stars: 140
  • Watchers: 6
  • Forks: 18
  • Open Issues: 1
  • Releases: 38
Topics
deep-learning directed-networks gnn graph-neural-netowrks machine-learning networks python pytorch pytorch-geometric signed-networks
Created over 4 years ago · Last pushed about 1 year ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

CI codecov Documentation Status PyPI Version Contributing

Documentation | Case Study | Data Set Descriptions | Installation | Data Structures | External Resources | Paper

PyTorch Geometric Signed Directed is a signed and directed extension library for PyTorch Geometric. It follows the package structure in PyTorch Geometric Temporal.

The library consists of various signed and directed geometric deep learning, embedding, and clustering methods from a variety of published research papers and selected preprints.

We also provide detailed examples in the examples folder.

Citing

If you find PyTorch Geometric Signed Directed useful in your research, please consider adding the following citation:

bibtex @inproceedings{he2024pytorch, 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={Learning on Graphs Conference}, pages={12--1}, year={2024}, organization={PMLR} }

Methods Included

In detail, the following signed or directed graph neural networks, as well as related methods designed for signed or directed netwroks, were implemented.

Directed Unsigned Network Models and Layers

Expand to see all methods implemented for directed networks... * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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)

Signed (Directed) Network Models and Layers

Expand to see all methods implemented for signed networks... * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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)

Network Generation Methods

Data Loaders and Classes

Expand to see all data loaders and related methods... * **[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. * **[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. * **[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. * **[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. * **[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. * **[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. * **[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. * **[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. * **[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.

Task-Specific Objectives and Evaluation Methods

Expand to see all task-specific objectives and evaluation methods... * **[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) * **[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) * **[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. * **[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. * **[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. * **[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) * **[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) * **[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) * **[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) * **[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) * **[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)**

Utilities and Preprocessing Methods

Expand to see all utilities and preprocessing methods... * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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) * **[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)**

Head over to our documentation to find out more! If you notice anything unexpected, please open an issue. If you are missing a specific method, feel free to open a feature request.

Installation

Binaries are provided for Python version >= 3.7 and NetworkX version < 2.7.

After installing PyTorch and PyG, simply run

```sh pip install torch-geometric-signed-directed

```

Running tests

``` $ pytest

```

License

Owner

  • Name: Yixuan He
  • Login: SherylHYX
  • Kind: user
  • Location: Oxford
  • Company: University of Oxford

DPhil in Statistics @ University of Oxford

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "Please cite our paper if you find our work useful in your research."
title: "PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs"
authors:
- family-names: "He"
  given-names: "Yixuan"
- family-names: "Zhang"
  given-names: "Xitong"
- family-names: "Huang"
  given-names: "Junjie"
- family-nmes: "Rozemberczki"
  given-names: "Benedek"
- family-names: "Cucuringu"
  given-names: "Mihai"
- family-names: "Reinert"
  given-names: "Gesine"
license: MIT
url: "https://github.com/SherylHYX/pytorch_geometric_signed_directed"
preferred-citation:
  type: article
  authors:
  - family-names: "He"
    given-names: "Yixuan"
  - family-names: "Zhang"
    given-names: "Xitong"
  - family-names: "Huang"
    given-names: "Junjie"
  - family-nmes: "Rozemberczki"
    given-names: "Benedek"
  - family-names: "Cucuringu"
    given-names: "Mihai"
  - family-names: "Reinert"
    given-names: "Gesine"
  journal: "Learning on Graphs Conference"
  title: "PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs"
  year: 2024

GitHub Events

Total
  • Release event: 2
  • Watch event: 16
  • Delete event: 3
  • Issue comment event: 2
  • Push event: 21
  • Pull request event: 4
  • Fork event: 3
  • Create event: 4
Last Year
  • Release event: 2
  • Watch event: 16
  • Delete event: 3
  • Issue comment event: 2
  • Push event: 21
  • Pull request event: 4
  • Fork event: 3
  • Create event: 4

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 565
  • Total Committers: 5
  • Avg Commits per committer: 113.0
  • Development Distribution Score (DDS): 0.136
Past Year
  • Commits: 38
  • Committers: 1
  • Avg Commits per committer: 38.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
SherylHYX H****X@o****m 488
XitongZhang1994 x****5@w****u 32
huangjunjie-cs j****s@g****m 26
xtr12 z****t@m****u 18
huangjunjie-cs j****s@g****m 1
Committer Domains (Top 20 + Academic)
msu.edu: 1 wpi.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 4
  • Total pull requests: 61
  • Average time to close issues: 3 days
  • Average time to close pull requests: 3 days
  • Total issue authors: 3
  • Total pull request authors: 3
  • Average comments per issue: 3.0
  • Average comments per pull request: 0.74
  • Merged pull requests: 51
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 4
  • Average time to close issues: N/A
  • Average time to close pull requests: 14 minutes
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.5
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • ClaudMor (2)
  • mminici (1)
  • emalgorithm (1)
Pull Request Authors
  • XitongSystem (30)
  • SherylHYX (18)
  • huangjunjie-cs (15)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 202 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 37
  • Total maintainers: 3
pypi.org: torch-geometric-signed-directed

An Extension Library for PyTorch Geometric on signed and directed networks.

  • Versions: 37
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 202 Last month
Rankings
Stargazers count: 7.2%
Forks count: 9.3%
Dependent packages count: 10.0%
Average: 12.6%
Downloads: 14.9%
Dependent repos count: 21.7%
Maintainers (3)
SherylHYX yixuanhe zhangxit
Last synced: 6 months ago

Dependencies

.github/workflows/main.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • s-weigand/setup-conda v1 composite
.github/workflows/python-publish.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite
  • pypa/gh-action-pypi-publish 27b31702a0e7fc50959f5ad993c78deac1bdfc29 composite
docs/requirements.txt pypi
  • networkx *
  • numpy *
  • six *
  • sphinx ==4.0.2
  • sphinx_rtd_theme ==0.5.2
  • torch_geometric ==2.0.3
setup.py pypi
  • networkx ==2.6.3
  • numpy *
  • scipy *
  • sklearn *
  • torch *
  • torch_geometric *
  • torch_sparse *