Skip to content

Could you release your trained models #12

Open

Description

@navdeepkjohal

Hello,

I wish to work RNN-Logic model and do some analysis with it. But unfortunately, I do not have resources to train the RNN-Logic model for FB15K-237 and WN18RR datasets right now. Would it be possible for you to release the trained models (workspace folder and the data/Rules folder) that you obtained while training your model with the optimal hyper-parameters reported in your paper ? That would really help.

Activity

  1. mnqu commented on May 2, 2022

    @mnqu
    Collaborator

    Thanks for your interests in RNNLogic! I am wondering what kinds of data do you need? the trained predictor, trained generator, or the generated logic rules?

  2. navdeepkjohal commented on May 2, 2022

    @navdeepkjohal
    Author

    Hello,

    Thank you for replying back to me! I wish to run test step for 'RNNLogic with embeddings' in line 123-126 in main branch without training the model. And I aim to do it for each relation. Basically, I wish to run the test step of the algorithm 1: for each query use p_{\theta} to generate N rules and feed them to p_{w} for prediction. This would require the optimal trained parameters for both generator and the predictor. Thank you for your consideration.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions