problem of training both models of classifier_model annd Randomwalk_Word2vec

[intellectwood]

Hello, I am very admiring your work.But I notice last line of main.py can train both model of classifier_model and Randomwalk_Word2vec but setting loss=(loss, 1.0), (loss2, 0.0) can only train model of classifier_model, right?

Then here is my question, setting loss=(loss, 1.0), (loss2, 1.0), code got error:

And I want to know whether only one model of classifier_model perform better or both model?

[ruochiz]

Hi, Thank you for your interest. Yeah, with the newer version of tensorflow, I stopped maintaining the code for the random walk part. The answer is that if you use the model with the adj mode, then just the classifier_model would work well. If it's random walk based, then that part of the loss would also be preferred. A quick fix, might just be changing line 132 of main from

example_emb = model.forward_u(examples)

to

example_embed, _ = model.forward_u(examples)

In addition, main_torch.py get rid of the dependencies of tensorflow 1.0 which would be slightly more up to date (while losing support for the random walk part of the model)

[intellectwood]

Still can't run, got this error, have you tried?

Then I am interested in your new version removing random walk, is it because with the adj mode can show best result or training both models(classifier_model annd Randomwalk_Word2vec) improves little?

[ruochiz]

the latter. training both models while offer some advantages when we did the benchmarking in the paper. But in some later applications of the model to other datasets, I found that training one model is good enough on its own.