mlsanityData to 7 Oct 2026

node2vec: Scalable Feature Learning for Networks

arXiv 1607.00653 ↗First posted 3 Jul 2016cs.SI cs.LG stat.MLcited by 1,913

Not on the map. Why?

Abstract (arXiv)

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node's network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks.

Key facts. Cited by 1,913 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jul 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 426; 2022: 395; 2023: 366; 2024: 325; 2025: 249; 2026: 152.

1,913 papers.

Sort:

By area:

  1. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  2. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  3. 2021Graph Self-Supervised Learning: A Surveycited by 289
  4. 2021Graph Contrastive Learning Automatedcited by 287
  5. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  6. 2021A Survey on Deep Semi-supervised Learningcited by 250
  7. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  8. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  9. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  10. 2022Graph neural networks for materials science and chemistrycited by 181
  11. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 176
  12. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
38 more
  1. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  2. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  3. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 154
  4. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  5. 2021Graph Learning: A Surveycited by 140
  6. 2021Graph Unlearningcited by 129
  7. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  8. 2022Towards Better Evaluation for Dynamic Link Predictioncited by 120
  9. 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
  10. 2022How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervisioncited by 102
  11. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
  12. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  13. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  14. 2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
  15. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  16. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  17. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  18. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  19. 2022MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflictscited by 81
  20. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  21. 2021Graph Representation Learning in Biomedicinecited by 79
  22. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  23. 2022Fairness in Graph Mining: A Surveycited by 76
  24. 2021FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoderscited by 75
  25. 2022Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddingscited by 75
  26. 2022Expander Graph Propagationcited by 75
  27. 2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73
  28. 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
  29. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  30. 2021Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learningcited by 70
  31. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  32. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  33. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  34. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
  35. 2022A Survey on Graph Representation Learning Methodscited by 66
  36. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  37. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  38. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 62

50 most cited of 1,913 All 1,913 (JSON)