Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning

TL;DR

This paper introduces a unified reinforcement learning approach using graph-based methods to improve conversational recommendation systems by integrating decision-making for asking attributes and recommending items, leading to better scalability and stability.

Contribution

It formulates CRS decision-making as a single policy learning task and develops a dynamic weighted graph RL method with action selection strategies for efficiency.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Enhances scalability and stability of conversational recommender systems.

Effective in real-world E-Commerce application.

Abstract

Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attributes to ask, which items to recommend, and when to ask or recommend, at each conversation turn. However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure. In the light of these challenges, we propose to formulate these three decision-making problems in CRS as a unified policy learning task. In order to systematically integrate conversation and recommendation components, we develop a dynamic weighted graph based RL method to learn a policy to select the action at each conversation turn, either asking an attribute or recommending items. Further, to deal with the sample efficiency issue, we propose two action selection strategies for reducing the candidate action space according to the preference and entropy information. Experimental results on two benchmark CRS datasets and a real-world E-Commerce application show that the proposed method not only significantly outperforms state-of-the-art methods but also enhances the scalability and stability of CRS.