Year: 2022
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Bahaj, Adil, Lhazmir, Safae, Ghogho, Mounir
Institution: International University of Rabat
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4289446353