Enhancing Link Prediction with Fuzzy Graph Attention Networks and Dynamic Negative Sampling
This work addresses link prediction for network analysis, offering an incremental improvement by integrating fuzzy rough sets into graph neural networks.
The paper tackled the problem of suboptimal link prediction in complex networks by introducing Fuzzy Graph Attention Networks (FGAT) with dynamic negative sampling, resulting in superior accuracy that outperformed state-of-the-art baselines on research collaboration networks.
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.