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 SpacePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Graph Embedding | 19 | 17.12% |
Knowledge Graph Embedding | 18 | 16.22% |
Knowledge Graphs | 13 | 11.71% |
Link Prediction | 13 | 11.71% |
Knowledge Graph Completion | 11 | 9.91% |
Entity Embeddings | 4 | 3.60% |
Knowledge Graph Embeddings | 3 | 2.70% |
Translation | 3 | 2.70% |
Decoder | 2 | 1.80% |