TransE is an energy-based model that produces knowledge base embeddings. It models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Relationships are represented as translations in the embedding space: if $\left(h, \mathcal{l}, t\right)$ holds, the embedding of the tail entity $t$ should be close to the embedding of the head entity $h$ plus some vector that depends on the relationship $\mathcal{l}$.
Source: Translating Embeddings for Modeling Multi-relational DataPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Knowledge Graphs | 37 | 16.44% |
Graph Embedding | 30 | 13.33% |
Link Prediction | 28 | 12.44% |
Knowledge Graph Embedding | 26 | 11.56% |
Knowledge Graph Completion | 17 | 7.56% |
Translation | 13 | 5.78% |
Knowledge Graph Embeddings | 12 | 5.33% |
Entity Embeddings | 9 | 4.00% |
Knowledge Base Completion | 9 | 4.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |