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 | 16 | 20.00% |
Knowledge Graph Embedding | 15 | 18.75% |
Link Prediction | 13 | 16.25% |
Knowledge Graphs | 10 | 12.50% |
Knowledge Graph Completion | 8 | 10.00% |
Entity Embeddings | 4 | 5.00% |
Relational Reasoning | 2 | 2.50% |
Knowledge Graph Embeddings | 2 | 2.50% |
Graph Representation Learning | 1 | 1.25% |