DBRec: Dual-Bridging Recommendation via Discovering Latent Groups

TL;DR

DBRec is a novel recommendation model that enhances user and item representations by discovering latent groups and hierarchies, bridging sparse data issues and improving recommendation accuracy.

Contribution

It introduces a dual-bridging framework that simultaneously discovers latent user/item groups and hierarchies, integrating them with collaborative filtering in a unified model.

Findings

DBRec outperforms state-of-the-art models on real datasets.

Latent group discovery improves recommendation accuracy.

Hierarchical modeling enhances user/item representation quality.

Abstract

In recommender systems, the user-item interaction data is usually sparse and not sufficient for learning comprehensive user/item representations for recommendation. To address this problem, we propose a novel dual-bridging recommendation model (DBRec). DBRec performs latent user/item group discovery simultaneously with collaborative filtering, and interacts group information with users/items for bridging similar users/items. Therefore, a user's preference over an unobserved item, in DBRec, can be bridged by the users within the same group who have rated the item, or the user-rated items that share the same group with the unobserved item. In addition, we propose to jointly learn user-user group (item-item group) hierarchies, so that we can effectively discover latent groups and learn compact user/item representations. We jointly integrate collaborative filtering, latent group discovering and hierarchical modelling into a unified framework, so that all the model parameters can be learned toward the optimization of the objective function. We validate the effectiveness of the proposed model with two real datasets, and demonstrate its advantage over the state-of-the-art recommendation models with extensive experiments.