ComplEx model trained with a nuclear norm regularizer; A relation prediction objective is added on top of the commonly used 1vsAll objective.
Source: Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph RepresentationsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Graph Representation Learning | 1 | 12.50% |
Knowledge Base Completion | 1 | 12.50% |
Knowledge Graph Completion | 1 | 12.50% |
Knowledge Graph Embedding | 1 | 12.50% |
Knowledge Graph Embeddings | 1 | 12.50% |
Link Prediction | 1 | 12.50% |
Link Property Prediction | 1 | 12.50% |
Relational Reasoning | 1 | 12.50% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |