Positive and Negative Critiquing for VAE-based Recommenders

TL;DR

This paper introduces M&Ms-VAE+, an advanced generative model that enables both positive and negative critiquing in recommender systems, improving multi-step critiquing performance while maintaining recommendation quality.

Contribution

M&Ms-VAE+ extends previous models by modeling user dislikes and a novel self-supervised critiquing module, enabling effective positive and negative critiquing in recommendations.

Findings

M&Ms-VAE+ matches or exceeds M&Ms-VAE in recommendation and explanation performance.

It significantly outperforms in positive and negative multi-step critiquing.

The model effectively incorporates user dislikes for improved critiquing.

Abstract

Providing explanations for recommended items allows users to refine the recommendations by critiquing parts of the explanations. As a result of revisiting critiquing from the perspective of multimodal generative models, recent work has proposed M&Ms-VAE, which achieves state-of-the-art performance in terms of recommendation, explanation, and critiquing. M&Ms-VAE and similar models allow users to negatively critique (i.e., explicitly disagree). However, they share a significant drawback: users cannot positively critique (i.e., highlight a desired feature). We address this deficiency with M&Ms-VAE+, an extension of M&Ms-VAE that enables positive and negative critiquing. In addition to modeling users' interactions and keyphrase-usage preferences, we model their keyphrase-usage dislikes. Moreover, we design a novel critiquing module that is trained in a self-supervised fashion. Our experiments on two datasets show that M&Ms-VAE+ matches or exceeds M&Ms-VAE in recommendation and explanation performance. Furthermore, our results demonstrate that representing positive and negative critiques differently enables M&Ms-VAE+ to significantly outperform M&Ms-VAE and other models in positive and negative multi-step critiquing.