NetEmb Datasets

A collection of real-world networks/graphs for Network Embedding

by Chengbin HOU 2018

Why this repository

As a beginner who has just entered this field, it is time-consuming to find datasets from different websites. And it might be painful to transform different formats in some required format. In this repository, we directly provide one of commonly-used formats as used in OpenANE and OpenNE. We hope this saves your time.

One of commonly-used formats:

*--------------- Structural Info (each row) --------------------*
adjlist: node_id1 node_id2 node_id3 ... (neighbors of node_id1)
or edgelist: node_id1 node_id2 weight (weight is optional)
*--------------- Attribute Info (each row) ---------------------*
node_id1 attr1 attr2 ...
*--------------- Label Info (each row) -------------------------*
node_id1 label1 label2 ...

Please consider citing the following paper(s) if this repository is useful for your research.
For static networks:

@article{hou2020RoSANE,
  title={Ro{SANE}: Robust and Scalable Attributed Network Embedding for Sparse Networks},
  author={Hou, Chengbin and He, Shan and Tang, Ke},
  journal={Neurocomputing},
  year={2020},
  publisher={Elsevier},
  url={https://doi.org/10.1016/j.neucom.2020.05.080},
  doi={10.1016/j.neucom.2020.05.080},
}

For dynamic networks:

@article{hou2020glodyne,
    title={GloDyNE: Global Topology Preserving Dynamic Network Embedding},
    author={Hou, Chengbin and Zhang, Han and He, Shan and Tang, Ke},
    journal={IEEE Transactions on Knowledge and Data Engineering},
    year={2020},
    doi={10.1109/TKDE.2020.3046511}
}

@article{hou2021robust,
  title={Robust Dynamic Network Embedding via Ensembles},
  author={Hou, Chengbin and Fu, Guoji and Yang, Peng and He, Shan and Tang, Ke},
  journal={arXiv preprint arXiv:2105.14557},
  year={2021}
}

Original datasets

Due to the storage limit in Github, we only provide well-transformed files in the format as described above.
Nevertheless, we also offer the hyper-links to the corresponding original datasets before transformation: cora, citeseer, pubmed, dblp, and mit, stanford, nyu, uIllinois.

Contact me chengbin.hou10@foxmail.com, if you need python script for such transformation or any other questions.

Contribution

Please consider to contribute if you have dataset in the format as described above. We will announce your contribution in this repository.

Useful links to network/graph datasets

http://konect.cc/
http://networkrepository.com/
https://snap.stanford.edu/data/
http://snap.stanford.edu/biodata/index.html
https://linqs.soe.ucsc.edu/data
https://aminer.org/data
http://socialcomputing.asu.edu/pages/datasets
http://networkrepository.com/
http://cnets.indiana.edu/resources/data-repository/
https://sites.google.com/site/ucinetsoftware/datasets
http://vlado.fmf.uni-lj.si/pub/networks/data/
http://www.sociopatterns.org/datasets/
http://networksciencebook.com/translations/en/resources/data.html