Hyperbolic Contrastive Learning with Model-augmentation for Knowledge-aware Recommendation

TL;DR

This paper introduces a hyperbolic contrastive learning framework with model-augmentation for knowledge-aware recommendation, effectively capturing hierarchical graph structures and avoiding preference shifts, leading to significant performance improvements.

Contribution

It proposes a Lorentzian knowledge aggregation mechanism and three novel model-level augmentation techniques for hyperbolic contrastive learning in recommendation systems.

Findings

Maximum improvement of 11.03% over baselines

Effective representation of hierarchical graph structures

Avoidance of preference shifts during augmentation

Abstract

Benefiting from the effectiveness of graph neural networks (GNNs) and contrastive learning, GNN-based contrastive learning has become mainstream for knowledge-aware recommendation. However, most existing contrastive learning-based methods have difficulties in effectively capturing the underlying hierarchical structure within user-item bipartite graphs and knowledge graphs. Moreover, they commonly generate positive samples for contrastive learning by perturbing the graph structure, which may lead to a shift in user preference learning. To overcome these limitations, we propose hyperbolic contrastive learning with model-augmentation for knowledge-aware recommendation. To capture the intrinsic hierarchical graph structures, we first design a novel Lorentzian knowledge aggregation mechanism, which enables more effective representations of users and items. Then, we propose three model-level augmentation techniques to assist Hyperbolic contrastive learning. Different from the classical structure-level augmentation (e.g., edge dropping), the proposed model-augmentations can avoid preference shifts between the augmented positive pair. Finally, we conduct extensive experiments to demonstrate the superiority (maximum improvement of $11.03\%$) of proposed methods over existing baselines.