A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges

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. In addition, we examine the current challenges and discuss promising future directions.

Submmit to WIREs: Data Mining and Knowledge Discovery. This version of the article has been accepted, after peer review but is not the version of record. The final version will be available at: https://doi.org/10.1002/widm.70093. Paper list at Github: https://github.com/sunxiaobei/awesome-gnn-based-link-prediction

References in corpus (17)

• DeepWalk: Online Learning of Social Representations
• Link Prediction in Complex Networks: A Survey
• Clustering and preferential attachment in growing networks
• Session-based Recommendation with Graph Neural Networks
• Solving the apparent diversity-accuracy dilemma of recommender systems
• Global Context Enhanced Graph Neural Networks for Session-based Recommendation
• Exploiting Cross-Session Information for Session-based Recommendation with Graph Neural Networks
• Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation
• A Survey on Hyperlink Prediction
• Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
• Graph Foundation Models: Concepts, Opportunities and Challenges
• LPFormer: An Adaptive Graph Transformer for Link Prediction
• Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
• DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing
• Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
• Hierarchical Position Embedding of Graphs with Landmarks and Clustering for Link Prediction
• Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction