This package includes the work of the Gromov-Wasserstein factorization models for graph representation and downstream tasks like graph clustering and classification. The references are listed below. Feel free to cite them if this package is useful in your research.
Hongteng Xu, Jiachang Liu, Dixin Luo, Lawrence Carin. - "Representing Graphs via Gromov-Wasserstein Factorization", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022. [https://ieeexplore.ieee.org/document/9720092]
Hongteng Xu - "Gromov-Wasserstein Factorization Models for Graph Clustering", AAAI Conference on Artificial Intelligence (AAAI), 2020. [https://ojs.aaai.org/index.php/AAAI/article/view/6120]
The examples include clustering two graph datasets:
- AIDS (with node attributes)
- IMDB-BINARY (without node attributes)
More data can be found at [https://ls11-www.cs.tu-dortmund.de/staff/morris/graphkerneldatasets]
- matplotlib
- networkx
- numpy
- pandas
- pickle
- pytorch
- typing