[RGCN] [RHGNN] Fixed code runtime error

[J0kerFeng]

Description

[RGCN]: Add the ’fanout‘ attribute to configuration file to fix: "AttributeError: 'Config' object has no attribute 'fanout'" problem. The value of ’fanout‘ is set to -1 by default and will need to be changed in the future based on the model parameters. [RHGNN]: Adds the 'device' parameter to the 'dataloader' object in the 'link_prediction.py' file to fix: "RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!" problem.

Checklist

Please feel free to remove inapplicable items for your PR.

• [x] The PR title starts with [$CATEGORY] (such as [NN], [Model], [Doc], [Feature]])
• [x] Changes are complete (i.e. I finished coding on this PR)
• [x] All changes have test coverage
• [ ] Code is well-documented
• [x] To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change
• [ ] Related issue is referred in this PR
• [ ] If the PR is for a new model/paper, I've updated the example index here.

Changes

[J0kerFeng]

There seems to be another problem here. When running RHGNN on gpu, The following error occurs: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat1 in method wrapper_addmm)

I have updated PR to fix this problem.