Graph neural networks (GNNs) have proven to be an effective tool for enhancing the performance of recommender systems. However, these systems often suffer from popularity bias, leading to an unfair advantage for frequently interacted items, while overlooking high-quality but less popular items. In this paper, we propose a GNN-based recommendation model that disentangles popularity and quality to address this issue. Unlike existing methods that treat all long-tail items uniformly, our approach introduces an edge classification technique to differentiate between popularity bias and genuine quality disparities among items. Furthermore, it uses cost-sensitive learning to adjust the misclassification penalties, ensuring that underrepresented yet relevant items are not unfairly disregarded. Experimental results demonstrate improvements in fairness metrics by approximately $32\%$ on average across different scenarios while maintaining competitive accuracy, with only minor variations compared to state-of-the-art methods.

翻译：图神经网络（GNNs）已被证明是提升推荐系统性能的有效工具。然而，这些系统常受流行度偏差影响，导致频繁交互的物品获得不公平优势，而高质量但低流行度的物品被忽视。本文提出一种基于GNN的推荐模型，通过分离流行度与质量来解决该问题。与现有将所有长尾物品统一处理的方法不同，我们的方法引入边分类技术来区分物品间的流行度偏差与真实质量差异。此外，该方法采用代价敏感学习调整误分类惩罚，确保未被充分代表但相关的物品不被不公平地忽略。实验结果表明，在保持竞争性准确率的前提下，公平性指标在不同场景下平均提升约32%，且与最先进方法相比仅有微小变化。