LINE in TensorFlow
TensorFlow implementation of paper LINE: Large-scale Information Network Embedding by Jian Tang, et al.
You can see my slide on GDG DevFest 2017 for more detail about LINE and TensorFlow. Notice: code shown in the slide are pseudocode, minibatch and negative sampling are omitted in the slide.
Prerequisites
- Python 3.6
- TensorFlow 1.3.0
- Networkx
- NumPy
Setup
- Prepare a network using networkx. Write the graph to a file by nx.write_gpickle.
- Put the network file in
datafolder. - Run
line.py --graph_file graph.pklto start training.graph.pklis the name of your network file. - Embedding will be stored in
data/embedding_XXX-order.pkl. You can load it bypickle.load()in python.
References
- Tang, Jian, et al. "Line: Large-scale information network embedding." Proceedings of the 24th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2015.