TM-GCN
Repository:
Description
Pytorch code for the TM-GCN method, a Dynamic Graph Convolutional Networks formulated using the Tensor M-Product algebra.
- Tensor-tensor algebra for optimal representation and compression of multiway data, ME Kilmer, L Horesh, H Avron, E Newman, Proceedings of the National Academy of Science (PNAS), 2021, https://www.pnas.org/content/118/28/e2015851118.short
- Dynamic Graph Convolutional Networks using the tensor M-product, O Malik, S Ubaru, L Horesh, M Kilmer, H Avron, SIAM International Conference on Data Mining (SDM 21), 2021, https://epubs.siam.org/doi/abs/10.1137/1.9781611976700.82
- New tensor algebra changes the rules of data analysis, IBM Blog, https://research.ibm.com/blog/new-tensor-algebra
Main Contributors
Shashanka Ubaru, Osman Malik, Lior Horesh