HGCL: Hierarchical Graph Contrastive Learning for User-Item Recommendation

TL;DR

This paper introduces HGCL, a hierarchical graph contrastive learning approach that leverages item hierarchy structures to improve user-item recommendation accuracy, demonstrating superior results on benchmark datasets.

Contribution

HGCL is the first GCL method to explicitly incorporate hierarchical item structures into user-item recommendation models, enhancing their effectiveness.

Findings

HGCL outperforms baseline models on benchmark datasets.

Hierarchical item structures significantly improve recommendation accuracy.

The method effectively captures multi-resolution item similarities.

Abstract

Graph Contrastive Learning (GCL), which fuses graph neural networks with contrastive learning, has evolved as a pivotal tool in user-item recommendations. While promising, existing GCL methods often lack explicit modeling of hierarchical item structures, which represent item similarities across varying resolutions. Such hierarchical item structures are ubiquitous in various items (e.g., online products and local businesses), and reflect their inherent organizational properties that serve as critical signals for enhancing recommendation accuracy. In this paper, we propose Hierarchical Graph Contrastive Learning (HGCL), a novel GCL method that incorporates hierarchical item structures for user-item recommendations. First, HGCL pre-trains a GCL module using cross-layer contrastive learning to obtain user and item representations. Second, HGCL employs a representation compression and clustering method to construct a two-hierarchy user-item bipartite graph. Ultimately, HGCL fine-tunes user and item representations by learning on the hierarchical graph, and then provides recommendations based on user-item interaction scores. Experiments on three widely adopted benchmark datasets ranging from 70K to 382K nodes confirm the superior performance of HGCL over existing baseline models, highlighting the contribution of hierarchical item structures in enhancing GCL methods for recommendation tasks.