Learning methods should detect that the provided DAG contains variables with no attributes associated (because it is randonmly generated) and does not match the attributes of the provided data.

torch.nn.GRU 's input shape is [sequence_size, batch_size, hidden_size].
But your code such as https://github.com/Nrgeup/controllable-text-attribute-transfer/blob/master/method/mymodel-yelp/model2.py#L315
is [batch_size, sequence_size, hidden_size].
I think your code is something wrong...

Hi,

An error was throwed when I ran the main.py:
FileNotFoundError: [Errno 2] No such file or directory: '../wiki2bio/original_data/word_vocab.txt'

It seems that the file wiki2bio/original_data/word_vocab.txt is not included.

In factor analysis section, transpose W in X = ZW and perhaps introduce component score part in pca section to make link clearer.