Non-Negative Matrix Factorization for Link Prediction Preserving Row and Column Spaces

• Published in: Proceedings (IEEE International Conference on Data Mining) pp. 1451 - 1456
• Main Authors: Yan, Liping, Yu, Weiren
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2023
• Subjects: column space; Convergence; Data mining; link prediction; Mathematical models; non-negative matrix factorization; Predictive models; row space; Time complexity
• ISSN: 2374-8486
• DOI: 10.1109/ICDM58522.2023.00190

Non-negative Matrix Factorization (NMF) has been widely adopted for link prediction, aiming at finding multiple low-dimensional matrices whose product approximates the adjacency matrix of a network. Most existing NMF-based models incorporate auxiliary information with well-defined geometric meanings, but there is no evidence that they have reasonable mathematical interpretations. In this paper, we propose a model, NMF-CR, that incorporates both row-space and column-space information into the NMF framework. NMF-CR not only carries well-defined geometric meanings but also boasts a reasonable mathematical interpretation. Moreover, we provide efficient updating rules to infer the parameters of NMF-CR with guaranteed convergence. Extensive experiments demonstrate that our model achieves higher prediction accuracy than its competitors.