Bandit Learning for Diversified Interactive Recommendation

TL;DR

This paper introduces DC$^2$B, a diversified interactive recommendation model that uses determinantal point processes and Thompson sampling to enhance recommendation diversity and performance based on implicit feedback.

Contribution

The paper proposes a novel diversified recommendation model using determinantal point processes and a Thompson sampling algorithm with theoretical regret guarantees.

Findings

DC$^2$B effectively improves recommendation diversity.

The model achieves competitive accuracy in experiments.

Theoretical analysis confirms the model's performance guarantees.

Abstract

Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attentions. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsatisfying user experiences. In this paper, we propose a novel diversified recommendation model, named Diversified Contextual Combinatorial Bandit (DC$^2$B), for interactive recommendation with users' implicit feedback. Specifically, DC$^2$B employs determinantal point process in the recommendation procedure to promote diversity of the recommendation results. To learn the model parameters, a Thompson sampling-type algorithm based on variational Bayesian inference is proposed. In addition, theoretical regret analysis is also provided to guarantee the performance of DC$^2$B. Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed method.