Data to 7 Oct 2026

Link Prediction Based on Graph Neural Networks

arXiv 1802.09691 ↗First posted 27 Feb 2018cs.LG stat.MLcited by 829

Not on the map. Why?

Abstract (arXiv)

Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to their simplicity, interpretability, and for some of them, scalability. However, every heuristic has a strong assumption on when two nodes are likely to link, which limits their effectiveness on networks where these assumptions fail. In this regard, a more reasonable way should be learning a suitable heuristic from a given network instead of using predefined ones. By extracting a local subgraph around each target link, we aim to learn a function mapping the subgraph patterns to link existence, thus automatically learning a `heuristic' that suits the current network. In this paper, we study this heuristic learning paradigm for link prediction. First, we develop a novel γ-decaying heuristic theory. The theory unifies a wide range of heuristics in a single framework, and proves that all these heuristics can be well approximated from local subgraphs. Our results show that local subgraphs reserve rich information related to link existence. Second, based on the γ-decaying theory, we propose a new algorithm to learn heuristics from local subgraphs using a graph neural network (GNN). Its experimental results show unprecedented performance, working consistently well on a wide range of problems.

Key facts. Cited by 829 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 141; 2022: 159; 2023: 181; 2024: 181; 2025: 116; 2026: 51.

829 papers.

Sort:

By area:

2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
2021Identity-aware Graph Neural Networkscited by 197
2022How Powerful are Spectral Graph Neural Networkscited by 169
2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 153
2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
2021Nested Graph Neural Networkscited by 136
2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 127
2021Generative Causal Explanations for Graph Neural Networkscited by 124

38 more

2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 116
2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
2022Brain Network Transformercited by 92
2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
2024Position: Graph Foundation Models are Already Herecited by 84
2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
2021Mining Latent Structures for Multimedia Recommendationcited by 79
2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
2021Principled Simplicial Neural Networks for Trajectory Predictioncited by 77
2021A Review on Graph Neural Network Methods in Financial Applicationscited by 77
2023SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learningcited by 73
2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
2024A Survey of Large Language Models for Graphscited by 71
2021Learning from Counterfactual Links for Link Predictioncited by 69
2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
2022Relationformer: A Unified Framework for Image-to-Graph Generationcited by 67
2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
2022A Survey on Graph Representation Learning Methodscited by 66
2023Neural Common Neighbor with Completion for Link Predictioncited by 64
2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63
2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63

50 most cited of 829 All 829 (JSON)