Neural Metric Matrix Factorization

Abstract

Nowadays, matrix factorization(MF) has been widely adopted in industry and research as a classical collaborative filtering (CF) algorithm. Unfortunately, the dot product adopted by matrix factorization is against the triangle inequality, which is one of the main reasons why this model is opposed. To address the issue, we propose a recommendation algorithm combining metric learning and mf in the paper. It transforms users’ preferences into distances, using Euclidean distance which satisfies triangular inequalities instead of traditional dot products, then directly decomposes the distance matrix into latent factor matrices of users and items. A multi-layer feedforward neural network is adopted for learning the model. Extensive experiments on two real-world datasets show that the proposed model is obviously superior to some advanced models based on matrix factorization.