search

sjy1203 / GAMENet

GAMENet : Graph Augmented MEmory Networks for Recommending Medication Combination
MIT License
128 stars 43 forks source link

about the LEAP baseline #8

Open yuanyuansiyuan opened 4 years ago

yuanyuansiyuan commented 4 years ago

i also get the opensource original theano version of LEAP kdd2017: https://github.com/neozhangthe1/AutoPrescribe I have noticed that you two papers have the same cooperation authors. Can i just use your LEAP implementaion version instead of the theano version to test the leap model on my data? Wait for your response, thank you!

yuanyuansiyuan commented 4 years ago

Are these two implementation equal or have some difference in logic?

sjy1203 commented 4 years ago

To me, I think it's ok to use the leap model in this repository for your data. Technically, you can add the beam search technique to make the current implementation of LEAP equal to the one in the AutoPrescribe repository. Also, you could try different hyperparameters to accommodate the model to your data.

yuanyuansiyuan commented 4 years ago

i see, thank you very much for your explanation!