Attribute-aware Diversification for Sequential Recommendations

TL;DR

This paper introduces ADSR, a sequential recommender that balances accuracy and diversity by leveraging attribute information to diversify recommendations without sacrificing performance.

Contribution

It proposes a novel attribute-aware diversification method for sequential recommenders, addressing the lack of diversity consideration in prior accuracy-focused models.

Findings

ADSR achieves higher diversity in recommendations.

ADSR maintains comparable accuracy to existing methods.

Experimental results validate effectiveness on benchmark datasets.

Abstract

Users prefer diverse recommendations over homogeneous ones. However, most previous work on Sequential Recommenders does not consider diversity, and strives for maximum accuracy, resulting in homogeneous recommendations. In this paper, we consider both accuracy and diversity by presenting an Attribute-aware Diversifying Sequential Recommender (ADSR). Specifically, ADSR utilizes available attribute information when modeling a user's sequential behavior to simultaneously learn the user's most likely item to interact with, and their preference of attributes. Then, ADSR diversifies the recommended items based on the predicted preference for certain attributes. Experiments on two benchmark datasets demonstrate that ADSR can effectively provide diverse recommendations while maintaining accuracy.