SimKGC
What it is
SimKGC is a framework for Knowledge Graph Completion (KGC) that utilizes contrastive learning with pre-trained language models. It improves performance by combining a large number of negative samples with a hardness-aware InfoNCE loss.
The problem it solves
Inefficient contrastive learning in text-based knowledge graph completion.
What you could use it for
- Knowledge Graph Completion (KGC) tasks
- Text-based knowledge graph completion
- Contrastive learning for KG embeddings
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.