https://github.com/graph-0/rgtn-nie
Implementation for the paper: Representation Learning on Knowledge Graphs for Node Importance Estimation
https://github.com/graph-0/rgtn-nie
dgl-graph graph-transformer
Last synced: 11 months ago
JSON representation
Implementation for the paper: Representation Learning on Knowledge Graphs for Node Importance Estimation
- Host: GitHub
- URL: https://github.com/graph-0/rgtn-nie
- Owner: GRAPH-0
- Created: 2021-06-05T12:44:06.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2022-09-22T03:55:00.000Z (over 3 years ago)
- Last Synced: 2025-04-27T00:33:10.917Z (about 1 year ago)
- Topics: dgl-graph, graph-transformer
- Language: Python
- Homepage:
- Size: 12.6 MB
- Stars: 37
- Watchers: 6
- Forks: 14
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# RGTN-NIE
Dataset and code for Representation Learning on Knowledge Graphs for Node Importance Estimation.
## NIE Dataset
* FB15k: a subset from [FreeBase](https://developers.google.com/freebase).
* TMDB5k: original files are from
[Kaggle](https://www.kaggle.com/tmdb/tmdb-movie-metadata).
* IMDB: original files are from [IMDb Datasets](
https://www.imdb.com/interfaces/).
We provide the node text description files on [Google Drive](https://drive.google.com/file/d/10y6yIN6_y1Mw_83RKP32KISql_INjrWK/view?usp=sharing), and the graph construction files on [Google Drive](
https://drive.google.com/file/d/1xd0ObAIDYMsxQZD2l0e-9fWo_ro76--x/view?usp=sharing).
* Processed features: [Google Drive](https://drive.google.com/drive/folders/1mgcNhGHUTptTqRREJE-g-qKoGycVwKpV?usp=sharing).
Download the feature files and put them on 'datasets'.
## Dependencies
* pytorch 1.6.0
* DGL 0.5.3
## Training Examples
* run `sh train_geni.sh` for GENI in FB15k (full batch training)
* run `sh train_geni_batch.sh` for GENI in IMDB (minibatch training)
* run `sh train_two.sh` for RGTN in FB15k (full batch training)
* run `sh train_two_batch.sh` for RGTN in IMDB (minibatch training)
Note that hyperparameters may require grid search in small datasets.
## Citation
If you find our work useful for your reseach, please consider citing this paper:
```bibtex
@inproceedings{Huang21RGTN-NIE,
author = {Han Huang and Leilei Sun and Bowen Du and Chuanren Liu and Weifeng Lv and Hui Xiong},
title = {Representation Learning on Knowledge Graphs for Node Importance Estimation},
booktitle = {{KDD} '21: The 27th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore, August 14-18, 2021},
pages = {646--655},
publisher = {{ACM}},
year = {2021}
}
```