Training and Evaluation

Once the dataset instance is generated (for dataset instance generation, please refer to the previous section: Data Preparation), you can run models with XGCN’s APIs:

model = XGCN.create_model(config)                  # create model
model.fit()                                        # train
score, topk_node = model.infer_topk(k=100, src=5)  # inference

In this section, we are going to introduce:

• Model Configuration
• Model Training
• Model Evaluation
• Model Inference