search

cszhangzhen / ANRL

ANRL: Attributed Network Representation Learning via Deep Neural Networks(IJCAI-2018)
85 stars 19 forks source link

How to apply ANRL to Pubmed dataset? #9

Closed dlutcbl closed 4 years ago

dlutcbl commented 4 years ago

Excuse me, I wonder how to apply ANRL to Pubmed dataset? I changed the read_feature function to read Pubmed feature matrix like: features = sio.loadmat(inputFileName) features = features['feature'] I adjusted the parameter in tf.app,flags and changed the struct parameter in config.py to [None, 200 ,None]. However the result is confusing, please tell me what other operations should I do? Thanks a lot.

cszhangzhen commented 4 years ago

Hi,

To be consistent with citeseer dataset, I transform the features into 1 and 0 . Try to add the following line: features[features>0] = 1.0

Or you can normalize the features.

dlutcbl commented 4 years ago

Hi,

To be consistent with citeseer dataset, I transform the features into 1 and 0 . Try to add the following line: features[features>0] = 1.0

Or you can normalize the features.

Thanks for your advice, it works! Best wishes!

cszhangzhen commented 4 years ago

Feel free to let me know if you have any question 😊