Skip to content
Source code and datasets of IJCAI2017 paper "TransNet: Translation-Based Network Representation Learning for Social Relation Extraction".
Branch: master
Clone or download
Latest commit f94d481 Mar 25, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ipynb Add ipynb version of TransNet Aug 14, 2017
uai use a new dataset which has 1000 authors and 400 kinds of labels Jul 13, 2017
.DS_Store Add ipynb version of TransNet Aug 14, 2017
LICENSE Add LICENSE May 9, 2017
README.md Update README.md. Mar 25, 2018
aminer_raw.zip Add a raw dataset. Mar 25, 2018
data.zip Add datasets May 9, 2017
init.py Add source code May 9, 2017
train.py Add source code May 9, 2017

README.md

TransNet

Source code and datasets of IJCAI2017 paper "TransNet: Translation-Based Network Representation Learning for Social Relation Extraction".

This work is selected as an example of the “MLTrain” training event in UAI 2017 (The Conference on Uncertainty in Artificial Intelligence). We release an ipython notebook that demonstrates the algorithm of TransNet. Details please refer to the "ipynb" directory.

Datasets

This folder "data" contains three different scales of datasets extracted from Aminer. Please unzip the "data.zip" file before using it.

  • aminer_s: 187,939 vertices, 1,619,278 edges and 100 labels.
  • aminer_m: 268,037 vertices, 2,747,386 edges and 500 labels.
  • aminer_l: 945,589 vertices, 5,056,050 edges and 500 labels.

The mapping from authors to identifiers in aminer_s/m/l is lost. We offer a raw aminer dataset which contains 5000 labels of edges and 1,712,433 authors. The dataset is extracted from AMiner. Please unzip the "aminer_raw.zip" file before using it.

Run

Run the following command for training TransNet:

python train.py name_of_dataset alpha beta warm_up_to_reload transnet_to_reload

Here is an example:

python train.py aminer_s/ 0.5 20 -1 -1

Explanations of the parameters:

  • name_of_dataset: name of dataset ("aminer_s/", "aminer_m/" or "aminer_l/")
  • alpha: the weight of autoencoder loss
  • beta: the weight of non-zero element in autoencoder
  • warm_up_to_reload: if >=0, reload saved autoencoder parameters and skip warm-up process
  • transnet_to_reload: if >=0, reload saved TransNet parameters

Dependencies

  • Tensorflow == 0.12
  • Scipy == 0.18.1
  • Numpy == 1.11.2

Cite

If you use the code, please cite this paper:

Cunchao Tu, Zhengyan Zhang, Zhiyuan Liu, Maosong Sun. TransNet: Translation-Based Network Representation Learning for Social Relation Extraction. The 26th International Joint Conference on Artificial Intelligence (IJCAI 2017).

For more related works on network representation learning, please refer to my homepage.

You can’t perform that action at this time.