Arguments:
  --h-size DIM          Hidden embedding dimension
  --c C                 Curvature
  --x-size DIM          Input edimension
  --batch-size  BS      Batch size
  --data-dir DIR        Directory for data
  --device DEVICE       Device
  --lr LR               Learning rate
  --dropout DROPOUT     Dropout probability
  --epochs EPOCHS       Maximum number of epochs to train for
  --weight-decay WEIGHT_DECAY
                        L2 regularization strength
  --optimizer OPTIMIZER
                        Which optimizer to use
  --patience PATIENCE   Patience for early stopping
  --beta BETA           CB loss hyperparameter
  --gamma GAMMA         CB loss hyperparameter
  --save                Save computed results
  --save-dir SAVE_DIR   Path to save results
  --min-epochs MIN_EPOCHS
                        Do not early stop before min-epochs

@InProceedings{pmlr-v151-sawhney22a,
  title = { Orthogonal Multi-Manifold Enriching of Directed Networks },
  author = {Sawhney, Ramit and Agarwal, Shivam and Neerkaje, Atula T. and Jayesh Pathak, Kapil},
  booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics},
  pages = {6074--6086},
  year = {2022},
  editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel},
  volume = {151},
  series = {Proceedings of Machine Learning Research},
  month = {28--30 Mar},
  publisher = {PMLR},
  pdf = {https://proceedings.mlr.press/v151/sawhney22a/sawhney22a.pdf},
  url = {https://proceedings.mlr.press/v151/sawhney22a.html}
}