mlsanityData to 7 Oct 2026

Class-Imbalanced Learning on Graphs: A Survey

arXiv 2304.04300 ↗First posted 9 Apr 2023cs.LG cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

The rapid advancement in data-driven research has increased the demand for effective graph data analysis. However, real-world data often exhibits class imbalance, leading to poor performance of machine learning models. To overcome this challenge, class-imbalanced learning on graphs (CILG) has emerged as a promising solution that combines the strengths of graph representation learning and class-imbalanced learning. In recent years, significant progress has been made in CILG. Anticipating that such a trend will continue, this survey aims to offer a comprehensive understanding of the current state-of-the-art in CILG and provide insights for future research directions. Concerning the former, we introduce the first taxonomy of existing work and its connection to existing imbalanced learning literature. Concerning the latter, we critically analyze recent work in CILG and discuss urgent lines of inquiry within the topic. Moreover, we provide a continuously maintained reading list of papers and code at https://github.com/yihongma/CILG-Papers.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 51 of its 115 references that are in the map. First posted on arXiv 9 Apr 2023.

Builds on

51 of 115 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  10. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  12. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
38 more
  1. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  2. 2017Focal Loss for Dense Object Detectioncited by 749
  3. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  4. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  5. 2019Multi-scale Attributed Node Embeddingcited by 543
  6. 2018Hypergraph Neural Networkscited by 482
  7. 2021Deep Long-Tailed Learning: A Surveycited by 416
  8. 2018Deep Learning on Graphs: A Surveycited by 393
  9. 2021Graph Self-Supervised Learning: A Surveycited by 289
  10. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  11. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  12. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  13. 2021Delving into Deep Imbalanced Regressioncited by 157
  14. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  15. 2017A Survey on Network Embeddingcited by 142
  16. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  17. 2019Generative Adversarial Minority Oversamplingcited by 72
  18. 2018Imbalanced Deep Learning by Minority Class Incremental Rectificationcited by 65
  19. 2021Topology-Imbalance Learning for Semi-Supervised Node Classificationcited by 56
  20. 2021ImGAGN:Imbalanced Network Embedding via Generative Adversarial Graph Networkscited by 51
  21. 2022Graph-based Molecular Representation Learningcited by 51
  22. 2021Self-Damaging Contrastive Learningcited by 48
  23. 2022Heterogeneous Graph Masked Autoencoderscited by 47
  24. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  25. 2022Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashingcited by 31
  26. 2021Improving Contrastive Learning on Imbalanced Seed Data via Open-World Samplingcited by 30
  27. 2022LTE4G: Long-Tail Experts for Graph Neural Networkscited by 30
  28. 2021Imbalanced Graph Classification via Graph-of-Graph Neural Networkscited by 27
  29. 2020Network Embedding with Completely-imbalanced Labelscited by 21
  30. 2022ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classificationcited by 21
  31. 2022A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processingcited by 20
  32. 2022Graph Neural Network with Curriculum Learning for Imbalanced Node Classificationcited by 19
  33. 2023GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classificationcited by 19
  34. 2022Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networkscited by 12
  35. 2022TopoImb: Toward Topology-level Imbalance in Learning from Graphscited by 12
  36. 2022Model Optimization in Imbalanced Regressioncited by 7
  37. 2022Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learningcited by 4
  38. 2020Learning Attribute-Structure Co-Evolutions in Dynamic Graphscited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 7; 2025: 7; 2026: 5.

24 papers.

Sort:

By area:

  1. 2023HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networkscited by 32
  2. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  3. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  4. 2023BeMap: Balanced Message Passing for Fair Graph Neural Networkcited by 11
  5. 2024WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarkingcited by 5
  6. 2024Edge Classification on Graphs: New Directions in Topological Imbalancecited by 4
  7. 2024KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Datacited by 4
  8. 2024Krait: A Backdoor Attack Against Graph Prompt Tuningcited by 2
  9. 2024Class-Balanced and Reinforced Active Learning on Graphscited by 1
  10. 2024Automated Loss function Search for Class-imbalanced Node Classificationcited by 1
  11. 2024SaVe-TAG: LLM-based Interpolation for Long-Tailed Text-Attributed Graphscited by 1
  12. 2025GraphFedMIG: Tackling Class Imbalance in Federated Graph Learning via Mutual Information-Guided Generationcited by 1
12 more
  1. 2025SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regressioncited by 1
  2. 2026Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databasescited by 1
  3. 2023VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classificationcited by 0
  4. 2025Graph Learning for Bidirectional Disease Contact Tracing on Real Human Mobility Datacited by 0
  5. 2025UPL: Uncertainty-aware Pseudo-labeling for Imbalance Transductive Node Classificationcited by 0
  6. 2025When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Labelcited by 0
  7. 2025Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screeningcited by 0
  8. 2025Boosting Predictive Performance on Tabular Data through Data Augmentation with Latent-Space Flow-Based Diffusioncited by 0
  9. 2026H3: A Healthcare Three-Hop Index for Physician Referral Network Predictioncited by 0
  10. 2026On the Safety of Graph Representation Learningcited by 0
  11. 2026NodeImport: Imbalanced Node Classification with Node Importance Assessmentcited by 0
  12. 2026MDTE: Minority-Aware Diffusion over Temporal Edge Events for Imbalanced Node Classificationcited by 0