This repository is the implementation for paper Diffusion Maps for Textual Network Embedding.

• Tensorflow == 1.12
• python == 2.7

Run the following command for training:

python train.py

Run the following command for testing:

python auc.py

This folder "datasets" contains three datasets used in DMTE, including Cora, DBLP and Zhihu. In each dataset, there are two files named "data.txt" and "graph.txt".

• data.txt: Each line represents the text information of a vertex.
• graph.txt: The edgelist file of current social network.

Besides, there is an additional "group.txt" file in Cora and DBLP.

• group.txt: Each vertex in Cora has been annotated with a label. This file can be used for vertex classification.

The implementation of this paper is based on CANE.

Please cite our paper if it helps with your research

@inproceedings{zhang2018adversarial,
  title={Diffusion Maps for Textual Network Embedding},
  author={Zhang, Xinyuan and Li, Yitong and Shen, Dinghan and Carin, Lawrence},
  Booktitle={NeurIPS},
  year={2018}
}