Graph Embeddings

RotatE is a method for generating graph embeddings which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. The RotatE model is trained using a self-adversarial negative sampling technique.

Source: RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space


Paper Code Results Date Stars


Task Papers Share
Graph Embedding 19 17.92%
Knowledge Graph Embedding 18 16.98%
Link Prediction 13 12.26%
Knowledge Graphs 12 11.32%
Knowledge Graph Completion 11 10.38%
Entity Embeddings 4 3.77%
Knowledge Graph Embeddings 3 2.83%
Translation 3 2.83%
Sentence 2 1.89%