Hyper-Class Representation of Data

TL;DR

This paper introduces hyper-classes data representation, leveraging divergence measures to improve recommendation systems by providing more effective reference information, overcoming limitations of attribute-centered data processing.

Contribution

The paper proposes a novel hyper-classes data representation method using divergence measures, enhancing recommendation accuracy over traditional attribute-centered approaches.

Findings

Hyper-classes effectively capture data structure.

Improved recommendation performance demonstrated.

Method is efficient and promising.

Abstract

Data representation is usually a natural form with their attribute values. On this basis, data processing is an attribute-centered calculation. However, there are three limitations in the attribute-centered calculation, saying, inflexible calculation, preference computation, and unsatisfactory output. To attempt the issues, a new data representation, named as hyper-classes representation, is proposed for improving recommendation. First, the cross entropy, KL divergence and JS divergence of features in data are defined. And then, the hyper-classes in data can be discovered with these three parameters. Finally, a kind of recommendation algorithm is used to evaluate the proposed hyper-class representation of data, and shows that the hyper-class representation is able to provide truly useful reference information for recommendation systems and makes recommendations much better than existing algorithms, i.e., this approach is efficient and promising.