mlsanityData to 7 Oct 2026

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

arXiv 1810.05997 ↗First posted 14 Oct 2018cs.LG stat.MLcited by 987

Not on the map. Why?

Abstract (arXiv)

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend. In this paper, we use the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters on par or lower than previous models. It leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models. Our implementation is available online.

Key facts. Cited by 987 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 154; 2022: 197; 2023: 202; 2024: 224; 2025: 118; 2026: 92.

987 papers.

Sort:

By area:

  1. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  2. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  3. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  4. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  5. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  6. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  7. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  8. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  9. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  10. 2021Graph Condensation for Graph Neural Networkscited by 150
  11. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  12. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
38 more
  1. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  2. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  3. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 131
  4. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  5. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  6. 2021Learning Graph Embeddings for Compositional Zero-shot Learningcited by 112
  7. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  8. 2021MagNet: A Neural Network for Directed Graphscited by 104
  9. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  10. 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
  11. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  12. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  13. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  14. 2021GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddingscited by 90
  15. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  16. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  17. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  18. 2024Position: Graph Foundation Models are Already Herecited by 84
  19. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  20. 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
  21. 2022Graph Attention Multi-Layer Perceptroncited by 82
  22. 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
  23. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  24. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  25. 2022Hierarchical Graph Transformer with Adaptive Node Samplingcited by 72
  26. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  27. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  28. 2024Can GNN be Good Adapter for LLMs?cited by 71
  29. 2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Frameworkcited by 69
  30. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  31. 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
  32. 2021Elastic Graph Neural Networkscited by 67
  33. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
  34. 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
  35. 2022A Survey on Graph Representation Learning Methodscited by 66
  36. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  37. 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
  38. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 64

50 most cited of 987 All 987 (JSON)