Attentive Autoencoders for Multifaceted Preference Learning in One-class Collaborative Filtering

TL;DR

This paper introduces AMA, an efficient autoencoder-based framework that captures multifaceted user preferences in one-class collaborative filtering using attention mechanisms, improving interpretability and competitiveness.

Contribution

The paper proposes AMA, a novel multi-modal autoencoder that explicitly models multiple user preference facets with attention, addressing scalability and interpretability issues in OC-CF.

Findings

AMA achieves competitive performance on real-world datasets.

The attention mechanism enhances interpretability of user preferences.

AMA effectively captures diverse user interests without increasing complexity.

Abstract

Most existing One-Class Collaborative Filtering (OC-CF) algorithms estimate a user's preference as a latent vector by encoding their historical interactions. However, users often show diverse interests, which significantly increases the learning difficulty. In order to capture multifaceted user preferences, existing recommender systems either increase the encoding complexity or extend the latent representation dimension. Unfortunately, these changes inevitably lead to increased training difficulty and exacerbate scalability issues. In this paper, we propose a novel and efficient CF framework called Attentive Multi-modal AutoRec (AMA) that explicitly tracks multiple facets of user preferences. Specifically, we extend the Autoencoding-based recommender AutoRec to learn user preferences with multi-modal latent representations, where each mode captures one facet of a user's preferences. By leveraging the attention mechanism, each observed interaction can have different contributions to the preference facets. Through extensive experiments on three real-world datasets, we show that AMA is competitive with state-of-the-art models under the OC-CF setting. Also, we demonstrate how the proposed model improves interpretability by providing explanations using the attention mechanism.