Quaternion-Based Self-Attentive Long Short-Term User Preference Encoding for Recommendation

TL;DR

This paper introduces a novel quaternion-based model for capturing both long-term and short-term user preferences in recommendation systems, leveraging quaternion representations for richer encoding and improved robustness.

Contribution

It proposes the first quaternion-based framework for modeling user preferences in recommendation, combining long-term and short-term interests with a gating mechanism and adversarial learning.

Findings

Outperforms 11 state-of-the-art baselines.

Improves HIT@1 by 8.43% and NDCG@1 by 10.27%.

Demonstrates effectiveness on six real-world datasets.

Abstract

Quaternion space has brought several benefits over the traditional Euclidean space: Quaternions (i) consist of a real and three imaginary components, encouraging richer representations; (ii) utilize Hamilton product which better encodes the inter-latent interactions across multiple Quaternion components; and (iii) result in a model with smaller degrees of freedom and less prone to overfitting. Unfortunately, most of the current recommender systems rely on real-valued representations in Euclidean space to model either user's long-term or short-term interests. In this paper, we fully utilize Quaternion space to model both user's long-term and short-term preferences. We first propose a QUaternion-based self-Attentive Long term user Encoding (QUALE) to study the user's long-term intents. Then, we propose a QUaternion-based self-Attentive Short term user Encoding (QUASE) to learn the user's short-term interests. To enhance our models' capability, we propose to fuse QUALE and QUASE into one model, namely QUALSE, by using a Quaternion-based gating mechanism. We further develop Quaternion-based Adversarial learning along with the Bayesian Personalized Ranking (QABPR) to improve our model's robustness. Extensive experiments on six real-world datasets show that our fused QUALSE model outperformed 11 state-of-the-art baselines, improving 8.43% at HIT@1 and 10.27% at NDCG@1 on average compared with the best baseline.