Selective Matrix Factorization for Multi-relational Data Fusion

Abstract

Matrix factorization based data fusion solutions can account for the intrinsic structures of multi-relational data sources, but most solutions equally treat these sources or prefer sparse ones, which may be irrelevant for the target task. In this paper, we introduce a Selective Matrix Factorization based Data Fusion approach (SelMFDF) to collaboratively factorize multiple inter-relational data matrices into low-rank representation matrices of respective object types and optimize the weights of them. To avoid preference to sparse data matrices, it additionally regularizes these low-rank matrices by approximating them to multiple intra-relational data matrices and also optimizes the weights of them. Both weights contribute to automatically integrate relevant data sources. Finally, it reconstructs the target relational data matrix using the optimized low-rank matrices. We applied SelMFDF for predicting inter-relations (lncRNA-miRNA interactions, functional annotations of proteins) and intra-relations (protein-protein interactions). SelMFDF achieves a higher AUROC (area under the receiver operating characteristics curve) by at least 5.88%, and larger AUPRC (area under the precision-recall curve) by at least 18.23% than other related and competitive approaches. The empirical study also confirms that SelMFDF can not only differentially integrate these relational data matrices, but also has no preference toward sparse ones.