Multi-Facet Recommender Networks with Spherical Optimization

TL;DR

This paper introduces MARS, a multi-facet recommender system that uses multiple metric spaces and spherical optimization to better capture complex user-item interactions from implicit feedback, significantly improving recommendation accuracy.

Contribution

The paper proposes a novel multi-facet framework with cross-facet similarity measurement and spherical optimization, addressing limitations of single-metric approaches in capturing diverse preferences.

Findings

Achieves up to 40% improvements in HR and nDCG metrics.

Demonstrates effectiveness across six real-world datasets.

Enhances robustness and accuracy of implicit feedback-based recommendations.

Abstract

Implicit feedback is widely explored by modern recommender systems. Since the feedback is often sparse and imbalanced, it poses great challenges to the learning of complex interactions among users and items. Metric learning has been proposed to capture user-item interactions from implicit feedback, but existing methods only represent users and items in a single metric space, ignoring the fact that users can have multiple preferences and items can have multiple properties, which leads to potential conflicts limiting their performance in recommendation. To capture the multiple facets of user preferences and item properties while resolving their potential conflicts, we propose the novel framework of Multi-fAcet Recommender networks with Spherical optimization (MARS). By designing a cross-facet similarity measurement, we project users and items into multiple metric spaces for fine-grained representation learning, and compare them only in the proper spaces. Furthermore, we devise a spherical optimization strategy to enhance the effectiveness and robustness of the multi-facet recommendation framework. Extensive experiments on six real-world benchmark datasets show drastic performance gains brought by MARS, which constantly achieves up to 40\% improvements over the state-of-the-art baselines regarding both HR and nDCG metrics.