Attentive Autoencoders for Multifaceted Preference Learning in One-class Collaborative Filtering
This work addresses the challenge of modeling diverse user interests in recommender systems, offering an incremental improvement in efficiency and interpretability for domain-specific applications.
The paper tackles the problem of capturing multifaceted user preferences in one-class collaborative filtering by proposing the Attentive Multi-modal AutoRec (AMA) framework, which uses multi-modal latent representations and attention to assign different contributions to observed interactions, achieving competitive performance with state-of-the-art models on three real-world datasets.
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.