https://github.com/MichSchli/RelationPrediction

Implementation of R-GCNs for Relational Link Prediction
https://github.com/MichSchli/RelationPrediction

Last synced: 6 days ago
JSON representation

Implementation of R-GCNs for Relational Link Prediction

• Host: GitHub
• URL: https://github.com/MichSchli/RelationPrediction
• Owner: MichSchli
• License: mit
• Created: 2016-09-09T11:34:37.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2023-03-24T16:28:10.000Z (over 1 year ago)
• Last Synced: 2024-08-02T08:10:12.588Z (3 months ago)
• Language: Python
• Homepage:
• Size: 23.1 MB
• Stars: 430
• Watchers: 10
• Forks: 103
• Open Issues: 15
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-gcn - MichSchli/RelationPrediction - GCNs for Relational Link Prediction (Knowledge Graph:)
• StarryDivineSky - MichSchli/RelationPrediction

README

        
# Graph Convolutional Networks for Relational Link Prediction

This repository contains a TensorFlow implementation of Relational Graph Convolutional Networks (R-GCN), as well as experiments on relational link prediction. The description of the model and the results can be found in our paper:

[Modeling Relational Data with Graph Convolutional Networks](https://arxiv.org/abs/1703.06103). Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling (ArXiv 2017)

**Requirements**

* TensorFlow (1.4)

**Running demo**

We provide a bash script to run a demo of our code. In the folder *settings*, a collection of configuration files can be found. The block diagonal model used in our paper is represented through the configuration file *settings/gcn_block.exp*. To run a given experiment, execute our bash script as follows:

```

bash run-train.sh \[configuration\]

```

We advise that training can take up to several hours and require a significant amount of memory.

**Citation**

Please cite our paper if you use this code in your own work:

```

@inproceedings{schlichtkrull2018modeling,

  title={Modeling relational data with graph convolutional networks},

  author={Schlichtkrull, Michael and Kipf, Thomas N and Bloem, Peter and {van den Berg}, Rianne and Titov, Ivan and Welling, Max},

  booktitle={The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3--7, 2018, Proceedings 15},

  pages={593--607},

  year={2018},

  organization={Springer}

}

```