mlsanityData to 7 Oct 2026

A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation

arXiv 2402.03358 ↗First posted 29 Jan 2024cs.SI cs.AI cs.DScited by 57

Not on the map. Why?

Abstract (arXiv)

Many real-world datasets can be naturally represented as graphs, spanning a wide range of domains. However, the increasing complexity and size of graph datasets present significant challenges for analysis and computation. In response, graph reduction, or graph summarization, has gained prominence for simplifying large graphs while preserving essential properties. In this survey, we aim to provide a comprehensive understanding of graph reduction methods, including graph sparsification, graph coarsening, and graph condensation. Specifically, we establish a unified definition for these methods and introduce a hierarchical taxonomy to categorize the challenges they address. Our survey then systematically reviews the technical details of these methods and emphasizes their practical applications across diverse scenarios. Furthermore, we outline critical research directions to ensure the continued effectiveness of graph reduction techniques, as well as provide a comprehensive paper list at urlhttps://github.com/Emory-Melody/awesome-graph-reduction. We hope this survey will bridge literature gaps and propel the advancement of this promising field.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 80 of its 159 references that are in the map. First posted on arXiv 29 Jan 2024.

Builds on

80 of 159 references.

References · 80

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  7. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  10. 2020Dataset Condensation with Gradient Matchingcited by 510
  11. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  12. 2021Dataset Condensation with Distribution Matchingcited by 362
38 more
  1. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  2. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 253
  3. 2020Dataset Meta-Learning from Kernel Ridge-Regressioncited by 230
  4. 2021Dataset Distillation with Infinitely Wide Convolutional Networkscited by 215
  5. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  6. 2020Data Augmentation for Graph Neural Networkscited by 200
  7. 2022Graph neural networks for materials science and chemistrycited by 181
  8. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  9. 2020Graph Clustering with Graph Neural Networkscited by 163
  10. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  11. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
  12. 2021Graph Condensation for Graph Neural Networkscited by 150
  13. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
  14. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  15. 2021A Unified Lottery Ticket Hypothesis for Graph Neural Networkscited by 118
  16. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  17. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  18. 2022Decoupling the Depth and Scope of Graph Neural Networkscited by 94
  19. 2023Data Distillation: A Surveycited by 86
  20. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  21. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  22. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 70
  23. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  24. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  25. 2022Graph Condensation via Receptive Field Distribution Matchingcited by 60
  26. 2017HARP: Hierarchical Representation Learning for Networkscited by 58
  27. 2018Spectrally approximating large graphs with smaller graphscited by 56
  28. 2021Graph Coarsening with Neural Networkscited by 55
  29. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 50
  30. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  31. 2023Data-centric AI: Perspectives and Challengescited by 43
  32. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 36
  33. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  34. 2023A Survey on Dataset Distillation: Approaches, Applications and Future Directionscited by 32
  35. 2019A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarseningcited by 31
  36. 2023Graph Condensation for Inductive Node Representation Learningcited by 31
  37. 2018MILE: A Multi-Level Framework for Scalable Graph Embeddingcited by 28
  38. 2016ProjE: Embedding Projection for Knowledge Graph Completioncited by 26

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 22; 2026: 14.

57 papers.

Sort:

By area:

  1. 2024Graph Machine Learning in the Era of Large Language Models (LLMs)cited by 33
  2. 2024Graph Transformers: A Surveycited by 32
  3. 2024Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Treescited by 30
  4. 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matchingcited by 28
  5. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
  6. 2024EXGC: Bridging Efficiency and Explainability in Graph Condensationcited by 20
  7. 2024Graph Sparsification via Mixture of Graphscited by 17
  8. 2025Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networkscited by 14
  9. 2024A Survey on Graph Condensationcited by 9
  10. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  11. 2024RobGC: Towards Robust Graph Condensationcited by 8
  12. 2025GCAL: Adapting Graph Models to Evolving Domain Shiftscited by 8
38 more
  1. 2024GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insightscited by 7
  2. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  3. 2025AutoG: Towards automatic graph construction from tabular datacited by 6
  4. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  5. 2025Scalable Graph Condensation with Evolving Capabilitiescited by 6
  6. 2024GCondenser: Benchmarking Graph Condensationcited by 5
  7. 2024TinyGraph: Joint Feature and Node Condensation for Graph Neural Networkscited by 5
  8. 2024Backdoor Graph Condensationcited by 5
  9. 2025Simple yet Effective Graph Distillation via Clusteringcited by 4
  10. 2025From Points to Places: Towards Human Mobility-Driven Spatiotemporal Foundation Models via Understanding Placescited by 3
  11. 2025ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstructioncited by 2
  12. 2025GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computingcited by 2
  13. 2025Spectral Neural Graph Sparsificationcited by 2
  14. 2024Scale-aware Message Passing For Graph Node Classificationcited by 1
  15. 2024Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNscited by 1
  16. 2024Training-free Heterogeneous Graph Condensation via Data Selectioncited by 1
  17. 2025Dynamic Graph Condensationcited by 1
  18. 2025PlaceRep: Geospatial Place Representation Learning from Large-Scale Point-of-Interest Datacited by 1
  19. 2025Multi-view Graph Condensation via Tensor Decompositioncited by 1
  20. 2025Graph-Coarsening Approach for the Capacitated Vehicle Routing Problem with Time Windowscited by 1
  21. 2026MK-SGC-SC: Multiple Kernel Guided Sparse Graph Construction in Spectral Clustering for Unsupervised Speaker Diarizationcited by 1
  22. 2024Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networkscited by 0
  23. 2024ScaleNet: Scale Invariance Learning in Directed Graphscited by 0
  24. 2024Extending Graph Condensation to Multi-Label Datasets: A Benchmark Studycited by 0
  25. 2025Efficient and Privacy-Preserved Link Prediction via Condensed Graphscited by 0
  26. 2025Inference-friendly Graph Compression for Graph Neural Networkscited by 0
  27. 2025GraphFLEx: Structure Learning Framework for Large Expanding Graphscited by 0
  28. 2025Towards Pre-trained Graph Condensation via Optimal Transportcited by 0
  29. 2025Adaptive Graph Coarsening for Efficient GNN Trainingcited by 0
  30. 2025Structure-Aware Cooperative Ensemble Evolutionary Optimization on Combinatorial Problems with Multimodal Large Language Modelscited by 0
  31. 2025BoolSkeleton: Boolean Network Skeletonization via Homogeneous Pattern Reductioncited by 0
  32. 2025Topological Spatial Graph Coarseningcited by 0
  33. 2026Fair Data Pre-Processing with Imperfect Attribute Spacecited by 0
  34. 2026Model-to-Data Distillation for Graph Neural Networkscited by 0
  35. 2026Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependencecited by 0
  36. 2026Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmarkcited by 0
  37. 2026SIR: Structured Image Representations for Explainable Robot Learningcited by 0
  38. 2026Heterogeneous Graph Condensation via Role-Aware Clusteringcited by 0

50 most cited of 57 All 57 (JSON)