Issues about SawETM and WHAI
Closed this issue · 2 comments
The email from Hjelkrem Tan, who is a PhD student in University of Oslo:
``
Dear Mr. Chaojie Wang,
I am a PhD student at the University of Oslo, Norway. I would very much like to use your PyDPM library in my research, as I have read several papers from you and your colleagues on topic models. Would you be able to answer some questions I have about the implementations in your GitHub repo?
I cannot find any implementation of SawETM in the PyDPM library. Are you planning to release this with PyDPM?
In pydpm/model/hybrid_pm/whai.py it seems that the implementation of the encoder does not include the stochastic downward part from the WHAI paper. Is this intentional or something you will change later?
I hope that you can clarify this for me. Thank you for your time!
With best regards,
Martine Hjelkrem Tan
PhD student, University of Oslo
Digital Signal Processing and Image Analysis Group
''
I have added an parameter named ``encode_prior'' to control whether to introduce the prior in the encoder of WHAI as shown in
https://github.com/BoChenGroup/PyDPM/blob/master/pydpm/example/Hybrid_PM/Weibull_Hybrid_Autoencoding_Inference/WHAI_Demo.py
For the implementation of SawETM, can u help to reproduce the code in https://github.com/BoChenGroup/SawETM as soon as possible?
The code of SawETM has been added in https://github.com/BoChenGroup/PyDPM/blob/master/pydpm/example/Hybrid_PM/Sawtooth_Embedding_Topic_Model/SawETM_Demo.py
and the feedback issues of Tan
``
Hi Chaojie,
Thank you for your reply. I will take a look at the new updates, and I’m looking forward to further improvements to pyDPM. It will be very useful!
I have a follow up question about your SawETM paper. From the original repo it seems like you did some testing on MNIST as well as text data. Since this was not included in the paper, do you have some insight into how those experiments went? I will do some quick experiments on this myself shortly.
M. Tan
''