Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation

TL;DR

This paper introduces VRICR, a novel variational Bayesian approach that dynamically refines incomplete knowledge graphs using dialogue context to improve conversational recommendations.

Contribution

It proposes a variational reasoning framework that leverages dialogue data to enhance incomplete KGs and adaptively select knowledge for better recommendations.

Findings

Improved recommendation accuracy on benchmark datasets

Effective dynamic knowledge reasoning conditioned on dialogue context

Enhanced handling of incomplete and sparse knowledge graphs

Abstract

Conversational recommender systems (CRSs) often utilize external knowledge graphs (KGs) to introduce rich semantic information and recommend relevant items through natural language dialogues. However, original KGs employed in existing CRSs are often incomplete and sparse, which limits the reasoning capability in recommendation. Moreover, only few of existing studies exploit the dialogue context to dynamically refine knowledge from KGs for better recommendation. To address the above issues, we propose the Variational Reasoning over Incomplete KGs Conversational Recommender (VRICR). Our key idea is to incorporate the large dialogue corpus naturally accompanied with CRSs to enhance the incomplete KGs; and perform dynamic knowledge reasoning conditioned on the dialogue context. Specifically, we denote the dialogue-specific subgraphs of KGs as latent variables with categorical priors for adaptive knowledge graphs refactor. We propose a variational Bayesian method to approximate posterior distributions over dialogue-specific subgraphs, which not only leverages the dialogue corpus for restructuring missing entity relations but also dynamically selects knowledge based on the dialogue context. Finally, we infuse the dialogue-specific subgraphs to decode the recommendation and responses. We conduct experiments on two benchmark CRSs datasets. Experimental results confirm the effectiveness of our proposed method.