Graph Embeddings
TransE
Introduced by Bordes et al. in Translating Embeddings for Modeling Multi-relational DataTransE 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 Data
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Knowledge Graphs | 38 | 16.45% |
| Graph Embedding | 31 | 13.42% |
| Link Prediction | 28 | 12.12% |
| Knowledge Graph Embedding | 27 | 11.69% |
| Knowledge Graph Completion | 17 | 7.36% |
| Translation | 13 | 5.63% |
| Knowledge Graph Embeddings | 12 | 5.19% |
| Entity Embeddings | 9 | 3.90% |
| Knowledge Base Completion | 9 | 3.90% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
