A Knowledge-Enhanced Recommendation Model with Attribute-Level Co-Attention

TL;DR

This paper introduces ACAM, a recommendation model that leverages attribute-level co-attention and knowledge graph attributes to improve recommendation accuracy beyond traditional item-level attention models.

Contribution

The paper presents a novel attribute-level co-attention mechanism integrated with knowledge graph attributes for enhanced recommendation performance.

Findings

ACAM outperforms state-of-the-art deep models on realistic datasets.

Attribute-level co-attention effectively captures attribute correlations.

Knowledge graph attributes improve user and item representations.

Abstract

Deep neural networks (DNNs) have been widely employed in recommender systems including incorporating attention mechanism for performance improvement. However, most of existing attention-based models only apply item-level attention on user side, restricting the further enhancement of recommendation performance. In this paper, we propose a knowledge-enhanced recommendation model ACAM, which incorporates item attributes distilled from knowledge graphs (KGs) as side information, and is built with a co-attention mechanism on attribute-level to achieve performance gains. Specifically, each user and item in ACAM are represented by a set of attribute embeddings at first. Then, user representations and item representations are augmented simultaneously through capturing the correlations between different attributes by a co-attention module. Our extensive experiments over two realistic datasets show that the user representations and item representations augmented by attribute-level co-attention gain ACAM's superiority over the state-of-the-art deep models.