Skip to content
forked from IBM/TM-GCN

Pytorch code for TM-GCN, a Dynamic Graph Convolutional Networks Using the Tensor M-Product

License

Notifications You must be signed in to change notification settings

OsmanMalik/TM-GCN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

TM-GCN

PyTorch code for the TM-GCN method, a dynamic graph convolutional network which uses the tensor M-product. For further information about the method, please see our paper:

@inproceedings{malik2021dynamic,
  title = {Dynamic Graph Convolutional Networks Using the Tensor {M}-Product},
  booktitle = {Proceedings of the 2021 {SIAM} International Conference on Data Mining ({SDM})},
  author = {Malik, Osman Asif and Ubaru, Shashanka and Horesh, Lior and Kilmer, Misha E. and Avron, Haim},
  year = {2021},
  pages = {729--737},
  doi = {10.1137/1.9781611976700.82}
}

The published version is available at https://doi.org/10.1137/1.9781611976700.82, and a preprint which includes supplementary material is available at https://arxiv.org/abs/1910.07643

If you use our code in any of your work, please reference our paper.

About

Pytorch code for TM-GCN, a Dynamic Graph Convolutional Networks Using the Tensor M-Product

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.7%
  • MATLAB 2.3%