Semi-supervised Collaborative Ranking with Push at Top

TL;DR

This paper introduces S^2COR, a semi-supervised collaborative ranking model that effectively leverages side information to improve cold-start recommendations in sparse and non-uniform rating scenarios.

Contribution

The paper proposes S^2COR, a novel semi-supervised ranking model that incorporates side information for better cold-start recommendation performance.

Findings

S^2COR outperforms state-of-the-art models on real-world datasets.

Significantly higher recommendation quality in cold-start scenarios.

Effectively handles non-random missing data using side information.

Abstract

Existing collaborative ranking based recommender systems tend to perform best when there is enough observed ratings for each user and the observation is made completely at random. Under this setting recommender systems can properly suggest a list of recommendations according to the user interests. However, when the observed ratings are extremely sparse (e.g. in the case of cold-start users where no rating data is available), and are not sampled uniformly at random, existing ranking methods fail to effectively leverage side information to transduct the knowledge from existing ratings to unobserved ones. We propose a semi-supervised collaborative ranking model, dubbed \texttt{S$^2$COR}, to improve the quality of cold-start recommendation. \texttt{S$^2$COR} mitigates the sparsity issue by leveraging side information about both observed and missing ratings by collaboratively learning the ranking model. This enables it to deal with the case of missing data not at random, but to also effectively incorporate the available side information in transduction. We experimentally evaluated our proposed algorithm on a number of challenging real-world datasets and compared against state-of-the-art models for cold-start recommendation. We report significantly higher quality recommendations with our algorithm compared to the state-of-the-art.