mlsanityData to 13 Oct 2026

A Survey on Graph Condensation

arXiv 2402.02000 ↗First posted 3 Feb 2024cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Analytics on large-scale graphs have posed significant challenges to computational efficiency and resource requirements. Recently, Graph condensation (GC) has emerged as a solution to address challenges arising from the escalating volume of graph data. The motivation of GC is to reduce the scale of large graphs to smaller ones while preserving essential information for downstream tasks. For a better understanding of GC and to distinguish it from other related topics, we present a formal definition of GC and establish a taxonomy that systematically categorizes existing methods into three types based on its objective, and classify the formulations to generate the condensed graphs into two categories as modifying the original graphs or synthetic completely new ones. Moreover, our survey includes a comprehensive analysis of datasets and evaluation metrics in this field. Finally, we conclude by addressing challenges and limitations, outlining future directions, and offering concise guidelines to inspire future research in this field.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Builds on 35 of its 48 references that are in the map. First posted on arXiv 3 Feb 2024.

Builds on

35 of 48 references.

References · 35

  1. 2020Dataset Condensation with Gradient Matchingcited by 512
  2. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 361
  3. 2019Representation Learning for Dynamic Graphs: A Surveycited by 262
  4. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  5. 2021Graph Condensation for Graph Neural Networkscited by 150
  6. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  7. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  8. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  9. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  10. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  11. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  12. 2021Understanding Pooling in Graph Neural Networkscited by 69
23 more
  1. 2022Graph Condensation via Receptive Field Distribution Matchingcited by 60
  2. 2019GraphZoom: A multi-level spectral approach for accurate and scalable graph embeddingcited by 58
  3. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  4. 2022A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinkingcited by 56
  5. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  6. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  7. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  8. 2018Graph Coarsening with Preserved Spectral Propertiescited by 41
  9. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  10. 2019A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarseningcited by 31
  11. 2023Graph Condensation for Inductive Node Representation Learningcited by 31
  12. 2018MILE: A Multi-Level Framework for Scalable Graph Embeddingcited by 28
  13. 2022CLNode: Curriculum Learning for Node Classificationcited by 24
  14. 2024Graph Condensation: A Surveycited by 23
  15. 2021Graph coarsening: From scientific computing to machine learningcited by 21
  16. 2021Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networkscited by 18
  17. 2023Graph Distillation with Eigenbasis Matchingcited by 16
  18. 2020Little Ball of Fur: A Python Library for Graph Samplingcited by 15
  19. 2023Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networkscited by 14
  20. 2019Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transportcited by 12
  21. 2023Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Trainingcited by 12
  22. 2019Coresets for Clustering in Graphs of Bounded Treewidthcited by 9
  23. 2023Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Trainingcited by 9

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 1.

9 papers.

  1. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
  2. 2024RobGC: Towards Robust Graph Condensationcited by 8
  3. 2024GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insightscited by 7
  4. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  5. 2024Backdoor Graph Condensationcited by 5
  6. 2026Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependencecited by 1
  7. 2024Extending Graph Condensation to Multi-Label Datasets: A Benchmark Studycited by 0
  8. 2025Efficient and Privacy-Preserved Link Prediction via Condensed Graphscited by 0
  9. 2025Adaptive Graph Coarsening for Efficient GNN Trainingcited by 0