DeepGraphLearning / KnowledgeGraphEmbedding

MIT License
1.24k stars 264 forks source link

confused about implementation of DistMult #41

Closed junkangwu closed 3 years ago

junkangwu commented 3 years ago

According to the model in distmult paper, $$score = h_s M_r h_o^T$$. However, in most papers about knowledge graph completion including the model in CompGCN, they are realized as a form of $$score = h_s r h_o^T$$. May I ask you about the insight behind your realization form?

Edward-Sun commented 3 years ago

The distmult model uses a diagonal matrix, so these two definitions are equivalent.