2022/07/29 by Adil Bahaj, Bahaj, Adil, Safae Lhazmir +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Neuroscience · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Bioinformatics and Genomic Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2207.14617
openalex publication_date 2022/07/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 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.