Link prediction is crucial for understanding complex networks but traditional Graph Neural Networks (GNNs) often rely on random negative sampling, leading to suboptimal performance. This paper introduces Fuzzy Graph Attention Networks (FGAT), a novel approach integrating fuzzy rough sets for dynamic negative sampling and enhanced node feature aggregation. Fuzzy Negative Sampling (FNS) systematically selects high-quality negative edges based on fuzzy similarities, improving training efficiency. FGAT layer incorporates fuzzy rough set principles, enabling robust and discriminative node representations. Experiments on two research collaboration networks demonstrate FGAT's superior link prediction accuracy, outperforming state-of-the-art baselines by leveraging the power of fuzzy rough sets for effective negative sampling and node feature learning.

翻译：链接预测对于理解复杂网络至关重要，但传统的图神经网络通常依赖随机负采样，导致性能欠佳。本文提出模糊图注意力网络，这是一种集成模糊粗糙集进行动态负采样和增强节点特征聚合的新方法。模糊负采样基于模糊相似度系统地选择高质量负边，从而提升训练效率。FGAT层融合模糊粗糙集原理，能够生成鲁棒且具有区分度的节点表示。在两个科研合作网络上的实验表明，FGAT在链接预测准确率上具有优越性，通过利用模糊粗糙集实现有效的负采样和节点特征学习，其性能超越了现有先进基线模型。