Abstract
Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse graph structures. To address this critical gap, this paper provides a comprehensive review of GNN-based link prediction from a novel and dedicated GNN perspective.
We propose an innovative taxonomy that categorizes recent advancements based on techniques and applications. From a technique perspective, we focus on key GNN encoder architectures, including GCN-based, GAE-based, GAT-based, and GFormer-based methods, discussing their strengths and limitations. From an application perspective, we highlight prominent use cases of link prediction in knowledge graphs and recommendation systems, demonstrating their real-world impact. Additionally, we examine the current challenges and discuss promising future directions.
Blogger's Review: This paper offers a profound analysis of GNNs in the realm of link prediction, filling a significant gap in the literature. By comparing different architectures, researchers can better understand the application potential of GNNs and the challenges they face, guiding future research directions.