How to extend to other dataset benchmarks?

[brenowca]

Hi, I am trying to apply the NLM to other graph datasets, but I am a little confused on how to do it given the structure of the training script.

For instance, could you please shed some light on how to adapt the running scripts for other datasets like the Countries dataset*, that are bigger than the cases you presented in the paper and are also fixed (not randomly generated during each epoch)?

Thank you in advance for your time :)

• Guillaume Bouchard, Sameer Singh, and Theo Trouillon. On approximate reasoning capabilities of low-rank vector spaces.AAAI Spring Symposium, 2015

[dhh1995]

Thanks for your interest in our work. To adapt the training script for new dataset, you need to have a dataset wrapper to take in the fixed dataset, specify the data format (input, label, etc.), provide the data to the trainer (take a look at how our data provider works), and change the network structure accordingly (by changing parameters like depth, etc.) for the new problem.