mlsanityData to 14 Oct 2026

Revisiting Link Prediction: A Data Perspective

arXiv 2310.00793 ↗First posted 1 Oct 2023cs.SI cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

Link prediction, a fundamental task on graphs, has proven indispensable in various applications, e.g., friend recommendation, protein analysis, and drug interaction prediction. However, since datasets span a multitude of domains, they could have distinct underlying mechanisms of link formation. Evidence in existing literature underscores the absence of a universally best algorithm suitable for all datasets. In this paper, we endeavor to explore principles of link prediction across diverse datasets from a data-centric perspective. We recognize three fundamental factors critical to link prediction: local structural proximity, global structural proximity, and feature proximity. We then unearth relationships among those factors where (i) global structural proximity only shows effectiveness when local structural proximity is deficient. (ii) The incompatibility can be found between feature and structural proximity. Such incompatibility leads to GNNs for Link Prediction (GNN4LP) consistently underperforming on edges where the feature proximity factor dominates. Inspired by these new insights from a data perspective, we offer practical instruction for GNN4LP model design and guidelines for selecting appropriate benchmark datasets for more comprehensive evaluations.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 37 of its 90 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

37 of 90 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  7. 2016Variational Graph Auto-Encoderscited by 1,382
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  10. 2018Link Prediction Based on Graph Neural Networkscited by 832
  11. 2015Image-based Recommendations on Styles and Substitutescited by 706
  12. 2019Neural Graph Collaborative Filteringcited by 661
25 more
  1. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  2. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  3. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
  4. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  5. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  6. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  7. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  8. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  9. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  10. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  11. 2022Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learningcited by 28
  12. 2022Geodesic Graph Neural Network for Efficient Graph Representation Learningcited by 19
  13. 2021Hashing-Accelerated Graph Neural Networks for Link Predictioncited by 14
  14. 2022Revisiting Neighborhood-based Link Prediction for Collaborative Filteringcited by 11
  15. 2017Leveraging Node Attributes for Incomplete Relational Datacited by 10
  16. 2018Cumulative effects of triadic closure and homophily in social networkscited by 10
  17. 2019Link Prediction via Higher-Order Motif Featurescited by 10
  18. 2023SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregationcited by 10
  19. 2023SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learningcited by 8
  20. 2016Structural Diversity and Homophily: A Study Across More than One Hundred Big Networkscited by 6
  21. 2019Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifscited by 5
  22. 2019Inequality is rising where social network segregation interacts with urban topologycited by 3
  23. 2020The Homophily Principle in Social Network Analysiscited by 3
  24. 2021The Paradox of Second-Order Homophily in Networkscited by 3
  25. 2022On the Effect of Triadic Closure on Network Segregationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 15; 2025: 8; 2026: 5.

29 papers.

Sort:

By area:

  1. 2024Position: Graph Foundation Models are Already Herecited by 86
  2. 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 49
  3. 2024Graph Machine Learning in the Era of Large Language Models (LLMs)cited by 33
  4. 2025On the Benefits of Attribute-Driven Graph Domain Adaptationcited by 19
  5. 2024Efficient Neural Common Neighbor for Temporal Graph Link Predictioncited by 18
  6. 2023LPFormer: An Adaptive Graph Transformer for Link Predictioncited by 17
  7. 2024Universal Link Predictor By In-Context Learning on Graphscited by 13
  8. 2024Mixture of Link Predictors on Graphscited by 10
  9. 2024UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphscited by 10
  10. 2024On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networkscited by 10
  11. 2024LinkGPT: Teaching Large Language Models To Predict Missing Linkscited by 9
  12. 2024Cross-Domain Graph Data Scaling: A Showcase with Diffusion Modelscited by 8
17 more
  1. 2026TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Modelscited by 7
  2. 2024A Pure Transformer Pretraining Framework on Text-attributed Graphscited by 6
  3. 2025Future Link Prediction Without Memory or Aggregationcited by 5
  4. 2024Reconsidering the Performance of GAE in Link Predictioncited by 4
  5. 2026AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learningcited by 4
  6. 2024VisGraphVar: A Benchmark Generator for Assessing Variability in Graph Analysis Using Large Vision-Language Modelscited by 3
  7. 2025Unveiling Mode Connectivity in Graph Neural Networkscited by 3
  8. 2025A Scalable Pretraining Framework for Link Prediction with Efficient Adaptationcited by 2
  9. 2026EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrievalcited by 2
  10. 2024Attribute-Enhanced Similarity Ranking for Sparse Link Predictioncited by 1
  11. 2025OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Predictioncited by 1
  12. 2024Towards Understanding Link Predictor Generalizability Under Distribution Shiftscited by 0
  13. 2025Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Predictioncited by 0
  14. 2025Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignmentcited by 0
  15. 2025A Community-Enhanced Graph Representation Model for Link Predictioncited by 0
  16. 2026Instance Discrimination for Link Predictioncited by 0
  17. 2026A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networkscited by 0