Big Data Mining and Analytics  2019, Vol. 2 Issue (3): 195-204    DOI: 10.26599/BDMA.2019.9020003
Efficient Preference Clustering via Random Fourier Features
Jingshu Liu, Li Wang*, Jinglei Liu
Jingshu Liu and Li Wang are with the College of Data Science, Taiyuan University of Technology, Jinzhong 030600, China. E-mail: liujingshu1997@163.com.
Jinglei Liu is with the School of Computer and Control Engineering, Yantai University, Yantai 264005, China. E-mail: jinglei_liu@sina.com.

Abstract

Approximations based on random Fourier features have recently emerged as an efficient and elegant method for designing large-scale machine learning tasks. Unlike approaches using the Nystr?m method, which randomly samples the training examples, we make use of random Fourier features, whose basis functions (i.e., cosine and sine ) are sampled from a distribution independent from the training sample set, to cluster preference data which appears extensively in recommender systems. Firstly, we propose a two-stage preference clustering framework. In this framework, we make use of random Fourier features to map the preference matrix into the feature matrix, soon afterwards, utilize the traditional $k$-means approach to cluster preference data in the transformed feature space. Compared with traditional preference clustering, our method solves the problem of insufficient memory and greatly improves the efficiency of the operation. Experiments on movie data sets containing 100 000 ratings, show that the proposed method is more effective in clustering accuracy than the Nystr?m and $k$-means, while also achieving better performance than these clustering approaches.

Received: 13 November 2018      Published: 06 January 2020
Corresponding Authors: Li Wang