Model: integrate HERO and HERO_homo into OpenHGNN

[jiajia101]

Description

This PR adds support for HERO and HERO_homo in OpenHGNN, including model integration, dataset adaptation, trainerflow implementation

This PR adapts HERO-related components to the OpenHGNN code structure so that they can be trained and evaluated within the framework.

Checklist

• The PR title starts with [$CATEGORY] (such as [NN], [Model], [Doc], [Feature]])
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage
• Code is well-documented
• 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

• Add HERO model implementation for OpenHGNN
• Add HERO_homo model implementation for OpenHGNN
• Add corresponding trainerflow implementations
• Add dataset loading/adaptation logic for HERO-related datasets
• Register the new models, datasets, layers, and trainerflows in OpenHGNN
• Update related config and experiment entry logic
• Update README/example index for the new model
• Verify that the model can be loaded and run in the OpenHGNN pipeline

Validation

Example command used for validation:

python main.py -m HERO -d Yelp4HERO -t node_classification -g 0
python main.py -m HERO_homo -d photo4HERO -t node_classification -g 0

Verified that:
dataset loading works correctly
the model can be registered and run successfully
the trainerflow works under the OpenHGNN framework