How to generate good ./pretrain data for new datasets?

xiangwang1223 / knowledge_graph_attention_network

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

MIT License

1.05k stars 309 forks source link

How to generate good ./pretrain data for new datasets? #34

Open zhaohan-xi opened 4 years ago

zhaohan-xi commented 4 years ago

Hi Dear Author,

I now want to implement KGAT with new KGs, but seems like the direct embedding cannot get good performance. As you mentioned in README.md, load the pretrained embeddings would be better for evaluation. Then for a new incoming KG, how to generate such pertained embeddings?

lyancynthia commented 3 years ago

@HarrialX Have you solved your question? Could you please share your solution?