Dominant model data loading and training problems

[YingtongDou]

@kayzliu
When I write the Dominant example, I find the following issues. Please fix/answer them accordingly.

1. The current process_graph function is dedicated to the BlogCatalog dataset, we need to write a general dataloader that could handle any PyG data object. The preprocessing code for BlogCatalog can be put into the dominant.py under /example.
2. When I run model.fit(), train_loss became NaN after 5-6 epochs.
3. How is the outlier label of BlogCatalog generated?
4. Should we train the model on clean data and evaluate it on data with outliers?

[kayzliu]

The BlogCatalog dataset is for code validation only. The labels make no sense. I have updated the code in the latest commit. It should work well with correct outlier labels. Shall we override the original labels in the dataset with outlier labels (in
pygod/utils/outlier_generator.py)?