search

awslabs / dgl-ke

High performance, easy-to-use, and scalable package for learning large-scale knowledge graph embeddings.
https://dglke.dgl.ai/doc/
Apache License 2.0
1.26k stars 194 forks source link

Literal embedding and Graph-BERT support? #91

Open dany-nonstop opened 4 years ago

dany-nonstop commented 4 years ago

Hi, guys, this looks like a great start of a powerful knowledge graph embedding libraray! Thanks for sharing it! My question is: many practical applications involve knowledge graphs with mixture of structured (knowledge graph itself) and unstructured literal data (attributes like description, name, date, and etc). Do you have any plan to support literal-enhanced embedding like LiteralE as well? thanks. The other interesting development is Graph-BERT, where attention on local subgraph is used instead of GCN. It seems to be more scalable. Will you coonsider supporting it? ps. both algorithms already have their source code available right now.

zheng-da commented 4 years ago

Thanks for your suggestions. We'll take a look at these models. We have plans to add GNN-based KGE models for knowledge graphs with node features.

dany-nonstop commented 4 years ago

thank you @zheng-da, you and your team's great work is highly appreciated!

AlexMRuch commented 4 years ago

This would be an awesome and very welcomed addition!