Skip to content
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs, ICML 2019
Branch: master
Clone or download
Latest commit 919d15b May 14, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
logs update code and datasets May 5, 2019
LICENSE Initial commit Apr 29, 2019
README.md Update README.md May 14, 2019
RSN4EA.ipynb update code and datasets May 5, 2019
RSN4KGC.ipynb
data.7z update code and datasets May 5, 2019
requirements update code and datasets May 5, 2019

README.md

RSN

Lingbing Guo, Zequn Sun, Wei Hu*. Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs. In: ICML 2019

INSTALLATION

  1. Please first install Python 3.5+, and then unpack data.7z.

  2. Type pip install -r requirements in shell to install required packages. Note that, when using Tensorflow 1.2+, the learning rate has to be re-adjusted. We suggest using tensorflow-gpu = 1.1.

RUNNING

  1. Run jupyter by typing jupyter notebook in shell.

  2. In the opened browser, click RSN4EA.ipynb for entity alignment, or RSN4KGC.ipynb for KG completion.

  3. The files RSN4EA.ipynb and RSN4KGC.ipynb record the latest results on DBP-WD (normal) and FB15K, respectively.

  4. You can also click 'Toolbar -> Kernel -> Restart&Run All' to run these two experiments.

DATA

  1. Limited by the space, we only uploaded FB15K for KG completion. For WN18 and FB15K-237, you can easily download them from the Internet.

  2. Change options.data_path or other options.* to run RSN on different datasets with different settings.

  3. For RSN4KGC.ipynb, we adopt a matrix filter method for evaluation, which may use more than 64GB memory.

  4. For entity alignment, V1 denotes the normal datasets, and V2 denotes the dense ones. Please use first 10% data of ref_ent_ids for validation.

CITATION

If you find our work useful, please cite it as follows:

@inproceedings{RSN,
	Author = {Lingbing Guo and Zequn Sun and Wei Hu},
	Booktitle = {ICML 2019},
	Title = {Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs},
	Year = {2019}
}
You can’t perform that action at this time.