pyg-team/pytorch_geometric

HANConv link prediction example

Open

#4.221 aberto em 8 de mar. de 2022

Ver no GitHub
 (4 comments) (0 reactions) (0 assignees)Python (3.514 forks)batch import
1 - Priority P1documentationfeaturehelp wanted

Métricas do repositório

Stars
 (19.985 stars)
Métricas de merge de PR
 (Mesclagem média 35d 1h) (14 fundiu PRs em 30d)

Description

📚 Describe the documentation issue

There is an example for how to use HANConv to do node classification: https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/han_imdb.py, and we also have an example for how to do link prediction with heterogeneous graph: https://github.com/pyg-team/pytorch_geometric/blob/master/examples/hetero/hetero_link_pred.py.

However, we have to do different transformations in the two examples. It is tricky to figure out how to do link prediction with HANConv.

Suggest a potential alternative/fix

I would suggest to have an example showing how to do link prediction with HANConv, especially how to do T.RandomLinkSplit and T.AddMetaPaths together.

Guia do colaborador