Graph-based Collaborative Ranking

TL;DR

This paper introduces GRank, a novel graph-based method for collaborative ranking that effectively models user priorities and improves recommendation quality in sparse data scenarios.

Contribution

GRank is a new graph-based approach that accurately models user priorities and works with ranking data, addressing limitations of previous methods.

Findings

Significant improvement over existing algorithms in recommendation accuracy

Effective modeling of user priorities in a tripartite graph

Robust performance with ranking-only data

Abstract

Data sparsity, that is a common problem in neighbor-based collaborative filtering domain, usually complicates the process of item recommendation. This problem is more serious in collaborative ranking domain, in which calculating the users similarities and recommending items are based on ranking data. Some graph-based approaches have been proposed to address the data sparsity problem, but they suffer from two flaws. First, they fail to correctly model the users priorities, and second, they cannot be used when the only available data is a set of ranking instead of rating values. In this paper, we propose a novel graph-based approach, called GRank, that is designed for collaborative ranking domain. GRank can correctly model users priorities in a new tripartite graph structure, and analyze it to directly infer a recommendation list. The experimental results show a significant improvement in recommendation quality compared to the state of the art graph-based recommendation algorithms and other collaborative ranking techniques.