TDCGL: Two-Level Debiased Contrastive Graph Learning for Recommendation

TL;DR

This paper introduces TDCGL, a novel two-level debiased contrastive graph learning approach for recommendation systems that effectively handles noisy knowledge graphs and long-tail distribution issues, improving performance.

Contribution

It proposes a two-level contrastive learning framework that models higher-order relations and reduces bias from sampling, advancing knowledge graph-based recommendation methods.

Findings

Outperforms state-of-the-art baselines on open-source datasets.

Demonstrates strong anti-noise capability in noisy environments.

Ablation studies confirm the importance of each contrastive learning level.

Abstract

knowledge graph-based recommendation methods have achieved great success in the field of recommender systems. However, over-reliance on high-quality knowledge graphs is a bottleneck for such methods. Specifically, the long-tailed distribution of entities of KG and noise issues in the real world will make item-entity dependent relations deviate from reflecting true characteristics and significantly harm the performance of modeling user preference. Contrastive learning, as a novel method that is employed for data augmentation and denoising, provides inspiration to fill this research gap. However, the mainstream work only focuses on the long-tail properties of the number of items clicked, while ignoring that the long-tail properties of total number of clicks per user may also affect the performance of the recommendation model. Therefore, to tackle these problems, motivated by the Debiased Contrastive Learning of Unsupervised Sentence Representations (DCLR), we propose Two-Level Debiased Contrastive Graph Learning (TDCGL) model. Specifically, we design the Two-Level Debiased Contrastive Learning (TDCL) and deploy it in the KG, which is conducted not only on User-Item pairs but also on User-User pairs for modeling higher-order relations. Also, to reduce the bias caused by random sampling in contrastive learning, with the exception of the negative samples obtained by random sampling, we add a noise-based generation of negation to ensure spatial uniformity. Considerable experiments on open-source datasets demonstrate that our method has excellent anti-noise capability and significantly outperforms state-of-the-art baselines. In addition, ablation studies about the necessity for each level of TDCL are conducted.