Multi-Level Graph Attention Network Contrastive Learning for Knowledge-Aware Recommendation

TL;DR

This paper introduces a multi-level graph contrastive learning framework that leverages knowledge graphs to improve recommendation accuracy by enhancing user and item representations through multi-view distillation and self-supervised learning.

Contribution

It proposes a novel multi-view graph contrastive learning approach with multi-level self-supervision to better model user preferences and entity relations in knowledge-aware recommendation systems.

Findings

Outperforms existing state-of-the-art methods on three public datasets.

Effective in modeling user preferences and entity relations.

Ablation studies confirm the contribution of each module.

Abstract

In recent years, the use of edge information provided by knowledge graphs together with the advantages of higher-order connectivity in graph neural networks for recommendation systems has become an important research direction. However, existing approaches are often limited by sparse labels, insufficient graph structure learning, and noisy entities in the knowledge graph, which reduce recommendation accuracy. To address these limitations, we propose a multi-view graph contrastive learning framework. The proposed method enhances user representations through multi-view knowledge graph distillation, enabling more accurate modeling of user preferences over entities and relations. The network aggregates neighborhood entity information to construct informative item representations. Furthermore, we design a multi-level self-supervised contrastive learning module that performs comparisons across three perspectives: Inter-Level, Intra-Level, and Interaction-Level. This design improves the model's ability to generalize across intra-class samples while increasing discrimination between inter-class samples, thereby enabling more effective multi-dimensional feature modeling. We conduct extensive experiments on three public datasets using both baseline and ablation settings. Experimental results demonstrate that the proposed framework consistently outperforms existing state-of-the-art methods. Ablation studies further verify the effectiveness of each module in the proposed model.