mlsanityData to 7 Oct 2026

Position-aware Graph Neural Networks

arXiv 1906.04817 ↗First posted 11 Jun 2019cs.LG cs.SI stat.MLcited by 203

Not on the map. Why?

Abstract (arXiv)

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here we propose Position-aware Graph Neural Networks (P-GNNs), a new class of GNNs for computing position-aware node embeddings. P-GNN first samples sets of anchor nodes, computes the distance of a given target node to each anchor-set,and then learns a non-linear distance-weighted aggregation scheme over the anchor-sets. This way P-GNNs can capture positions/locations of nodes with respect to the anchor nodes. P-GNNs have several advantages: they are inductive, scalable,and can incorporate node feature information. We apply P-GNNs to multiple prediction tasks including link prediction and community detection. We show that P-GNNs consistently outperform state of the art GNNs, with up to 66% improvement in terms of the ROC AUC score.

Key facts. Cited by 203 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 46; 2022: 58; 2023: 36; 2024: 34; 2025: 19; 2026: 10.

203 papers.

Sort:

By area:

  1. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  2. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  3. 2021Identity-aware Graph Neural Networkscited by 197
  4. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  5. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  6. 2023Graph Inductive Biases in Transformers without Message Passingcited by 150
  7. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  8. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  9. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
  10. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  11. 2021Federated Graph Classification over Non-IID Graphscited by 113
  12. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
38 more
  1. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  2. 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
  3. 2024Position: Graph Foundation Models are Already Herecited by 84
  4. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  5. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  6. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  7. 2022BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networkscited by 73
  8. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  9. 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
  10. 2022A Survey on Graph Representation Learning Methodscited by 66
  11. 2021Reconstruction for Powerful Graph Representationscited by 65
  12. 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Testscited by 64
  13. 2021Language-Agnostic Representation Learning of Source Code from Structure and Contextcited by 63
  14. 2022Ordered Subgraph Aggregation Networkscited by 57
  15. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  16. 2022Neighborhood-aware Scalable Temporal Network Representation Learningcited by 54
  17. 2021On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphscited by 49
  18. 2021Knowledge-aware Coupled Graph Neural Network for Social Recommendationcited by 49
  19. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  20. 2022GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generationcited by 43
  21. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  22. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  23. 2022Rewiring with Positional Encodings for Graph Neural Networkscited by 35
  24. 2022T2-GNN: Graph Neural Networks for Graphs with Incomplete Features and Structure via Teacher-Student Distillationcited by 32
  25. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  26. 2023Path Neural Networks: Expressive and Accurate Graph Neural Networkscited by 32
  27. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  28. 2023On the Stability of Expressive Positional Encodings for Graphscited by 31
  29. 2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 27
  30. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  31. 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
  32. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 23
  33. 2021ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extractioncited by 22
  34. 2021PhysGNN: A Physics-Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image-Guided Neurosurgerycited by 22
  35. 2023Data-centric Graph Learning: A Surveycited by 22
  36. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  37. 2023Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embeddingcited by 21
  38. 2025Learning Efficient Positional Encodings with Graph Neural Networkscited by 21

50 most cited of 203 All 203 (JSON)