mlsanityData to 7 Oct 2026

Deep Graph Infomax

arXiv 1809.10341 ↗First posted 27 Sep 2018stat.ML cs.IT cs.LGcited by 1,101

Not on the map. Why?

Abstract (arXiv)

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

Key facts. Cited by 1,101 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 172; 2022: 237; 2023: 218; 2024: 202; 2025: 162; 2026: 110.

1,101 papers.

Sort:

By area:

  1. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  2. 2021Graph Self-Supervised Learning: A Surveycited by 289
  3. 2021Graph Contrastive Learning Automatedcited by 287
  4. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  5. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  6. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  7. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 184
  8. 2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
  9. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  10. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  11. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  12. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
38 more
  1. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  2. 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 138
  3. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  4. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  5. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  6. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 132
  7. 2023GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learnercited by 131
  8. 2021Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learningcited by 130
  9. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  10. 2021Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysiscited by 130
  11. 2022A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Languagecited by 129
  12. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  13. 2021Self-supervised Graph-level Representation Learning with Local and Global Structurecited by 125
  14. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  15. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  16. 2021Advances and Challenges in Conversational Recommender Systems: A Surveycited by 118
  17. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  18. 2022Towards Unsupervised Deep Graph Structure Learningcited by 112
  19. 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
  20. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
  21. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  22. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  23. 2021Augmentation-Free Self-Supervised Learning on Graphscited by 94
  24. 2021Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Datacited by 86
  25. 2022Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learningcited by 86
  26. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  27. 2024Position: Graph Foundation Models are Already Herecited by 84
  28. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  29. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 83
  30. 2021HDMI: High-order Deep Multiplex Infomaxcited by 82
  31. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  32. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 82
  33. 2021SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanismcited by 75
  34. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  35. 2022Expander Graph Propagationcited by 75
  36. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  37. 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
  38. 2021AutoGCL: Automated Graph Contrastive Learning via Learnable View Generatorscited by 73

50 most cited of 1,101 All 1,101 (JSON)