用模糊集动态选负样本，提升链接预测准确率
Enhancing Link Prediction with Fuzzy Graph Attention Networks and Dynamic Negative Sampling
- 引入模糊相似度动态选择高质量负样本
- 在两个合作网络上比现有方法准确率更高
- 适合做复杂网络链接预测的研究者参考
链接预测对理解复杂网络至关重要，但传统图神经网络常依赖随机负采样，导致性能不佳。本文提出模糊图注意力网络（FGAT），融合模糊粗糙集实现动态负采样与增强节点特征聚合。模糊负采样（FNS）基于模糊相似度系统性地选取高质量负边，提升训练效率。FGAT层引入模糊粗糙集原理，生成鲁棒且具有区分性的节点表示。在两个科研合作网络上的实验表明，FGAT通过模糊粗糙集有效实现负采样与节点特征学习，显著优于当前最优基线方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。