Interface for DE-GNN framework [-h] [--dataset DATASET] [--test_ratio TEST_RATIO]
                                      [--model {DE-GNN,GIN,GCN,GraphSAGE,GAT}] [--layers LAYERS]
                                      [--hidden_features HIDDEN_FEATURES] [--metric {acc,auc}] [--seed SEED] [--gpu GPU]
                                      [--data_usage DATA_USAGE] [--directed DIRECTED] [--parallel] [--prop_depth PROP_DEPTH]
                                      [--use_degree USE_DEGREE] [--use_attributes USE_ATTRIBUTES] [--feature FEATURE]
                                      [--rw_depth RW_DEPTH] [--max_sp MAX_SP] [--epoch EPOCH] [--bs BS] [--lr LR]
                                      [--optimizer OPTIMIZER] [--l2 L2] [--dropout DROPOUT] [--k K] [--n [N [N ...]]]
                                      [--N N] [--T T] [--log_dir LOG_DIR] [--summary_file SUMMARY_FILE] [--debug]

  -h, --help            show this help message and exit
  
  # general settings
  --dataset DATASET     dataset name
  --test_ratio TEST_RATIO
                        ratio of the test against whole
  --model {DE-GCN,GIN,GAT,GCN,GraphSAGE}
                        model to use
  --layers LAYERS       largest number of layers
  --hidden_features HIDDEN_FEATURES
                        hidden dimension
  --metric {acc,auc}    metric for evaluating performance
  --seed SEED           seed to initialize all the random modules
  --gpu GPU             gpu id
  --adj_norm {asym,sym,None}
                        how to normalize adj
  --data_usage DATA_USAGE
                        use partial dataset
  --directed DIRECTED   (Currently unavailable) whether to treat the graph as directed
  --parallel            (Currently unavailable) whether to use multi cpu cores to prepare data
  
  # positional encoding settings
  --prop_depth PROP_DEPTH
                        propagation depth (number of hops) for one layer
  --use_degree USE_DEGREE
                        whether to use node degree as the initial feature
  --use_attributes USE_ATTRIBUTES
                        whether to use node attributes as the initial feature
  --feature FEATURE     distance encoding category: shortest path or random walk (landing probabilities)
  --rw_depth RW_DEPTH   random walk steps
  --max_sp MAX_SP       maximum distance to be encoded for shortest path feature
  
  # training settings
  --epoch EPOCH         number of epochs to train
  --bs BS               minibatch size
  --lr LR               learning rate
  --optimizer OPTIMIZER
                        optimizer to use
  --l2 L2               l2 regularization weight
  --dropout DROPOUT     dropout rate
  
  # imulation settings (valid only when dataset == 'simulation')
  --k K                 node degree (k) or synthetic k-regular graph
  --n [N [N ...]]       a list of number of nodes in each connected k-regular subgraph
  --N N                 total number of nodes in simultation
  --T T                 largest number of layers to be tested
  
  # logging
  --log_dir LOG_DIR     log directory
  --summary_file SUMMARY_FILE
                        brief summary of training result
  --debug               whether to use debug mode

@article{li2020distance,
  title={Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning},
  author={Li, Pan and Wang, Yanbang and Wang, Hongwei and Leskovec, Jure},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  year={2020}
}