mlsanityData to 14 Oct 2026

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

arXiv 2607.16198 ↗First posted 29 Apr 2026cs.AI cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 54 of its 126 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

54 of 126 references.

References · 54

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  7. 2017Graph Attention Networkscited by 8,923
  8. 2017Inductive Representation Learning on Large Graphscited by 6,320
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  10. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  11. 2016Variational Graph Auto-Encoderscited by 1,382
  12. 2020Benchmarking Graph Neural Networkscited by 680
38 more
  1. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  2. 2017Neural Attentive Session-based Recommendationcited by 237
  3. 2020Can Graph Neural Networks Count Substructures?cited by 236
  4. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  5. 2020Complex Query Answering with Neural Link Predictorscited by 99
  6. 2021UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendationcited by 87
  7. 2020Bridging Knowledge Graphs to Generate Scene Graphscited by 86
  8. 2021Global Context Enhanced Graph Neural Networks for Session-based Recommendationcited by 81
  9. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  10. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  11. 2021A Survey on Embedding Dynamic Graphscited by 60
  12. 2021Neural Link Prediction with Walk Poolingcited by 37
  13. 2022Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selectioncited by 26
  14. 2021Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendationcited by 22
  15. 2021Exploiting Cross-Session Information for Session-based Recommendation with Graph Neural Networkscited by 20
  16. 2024Efficient Neural Common Neighbor for Temporal Graph Link Predictioncited by 18
  17. 2023LPFormer: An Adaptive Graph Transformer for Link Predictioncited by 17
  18. 2022Link Prediction on Heterophilic Graphs via Disentangled Representation Learningcited by 13
  19. 2022Line Graph Contrastive Learning for Link Predictioncited by 13
  20. 2023Adapting Neural Link Predictors for Data-Efficient Complex Query Answeringcited by 13
  21. 2022FakeEdge: Alleviate Dataset Shift in Link Predictioncited by 12
  22. 2023A Topological Perspective on Demystifying GNN-Based Link Prediction Performancecited by 11
  23. 2022Sampling Enclosing Subgraphs for Link Predictioncited by 9
  24. 2022A Survey on Hyperlink Predictioncited by 9
  25. 2023Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Predictioncited by 9
  26. 2023Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphscited by 9
  27. 2023Combating Bilateral Edge Noise for Robust Link Predictioncited by 9
  28. 2024Conformalized Link Prediction on Graph Neural Networkscited by 9
  29. 2024Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancementcited by 9
  30. 2022Efficient On-Device Session-Based Recommendationcited by 8
  31. 2023Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Predictioncited by 8
  32. 2022DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typingcited by 7
  33. 2022Disconnected Emerging Knowledge Graph Oriented Inductive Link Predictioncited by 7
  34. 2021Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Predictioncited by 4
  35. 2023Learning Scalable Structural Representations for Link Prediction with Bloom Signaturescited by 4
  36. 2024Learning Rule-Induced Subgraph Representations for Inductive Relation Predictioncited by 4
  37. 2024Reconsidering the Performance of GAE in Link Predictioncited by 4
  38. 2020Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graphcited by 3

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.