KG-NSF: Knowledge Graph Completion with a Negative-Sample-Free Approach
This addresses the computational inefficiency and bias in knowledge graph embedding methods, which is important for fields like biomedical research, though it appears incremental as it builds on existing embedding approaches.
The paper tackled the problem of knowledge graph completion by proposing KG-NSF, a negative-sample-free framework that avoids the computational and bias issues of negative sampling, achieving comparable link prediction performance with faster convergence.
Knowledge Graph (KG) completion is an important task that greatly benefits knowledge discovery in many fields (e.g. biomedical research). In recent years, learning KG embeddings to perform this task has received considerable attention. Despite the success of KG embedding methods, they predominantly use negative sampling, resulting in increased computational complexity as well as biased predictions due to the closed world assumption. To overcome these limitations, we propose \textbf{KG-NSF}, a negative sampling-free framework for learning KG embeddings based on the cross-correlation matrices of embedding vectors. It is shown that the proposed method achieves comparable link prediction performance to negative sampling-based methods while converging much faster.