mlsanityData to 13 Oct 2026

Graph Condensation via Receptive Field Distribution Matching

arXiv 2206.13697 ↗First posted 28 Jun 2022cs.LG cs.AIcited by 60

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) enable the analysis of graphs using deep learning, with promising results in capturing structured information in graphs. This paper focuses on creating a small graph to represent the original graph, so that GNNs trained on the size-reduced graph can make accurate predictions. We view the original graph as a distribution of receptive fields and aim to synthesize a small graph whose receptive fields share a similar distribution. Thus, we propose Graph Condesation via Receptive Field Distribution Matching (GCDM), which is accomplished by optimizing the synthetic graph through the use of a distribution matching loss quantified by maximum mean discrepancy (MMD). Additionally, we demonstrate that the synthetic graph generated by GCDM is highly generalizable to a variety of models in evaluation phase and that the condensing speed is significantly improved using this framework.

Key facts. Cited by 60 papers in the map (data through 13 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

23 of 35 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  2. 2017Inductive Representation Learning on Large Graphscited by 6,303
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
  4. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,323
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,157
  6. 2019Simplifying Graph Convolutional Networkscited by 1,474
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 991
  9. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  10. 2019Gradient based sample selection for online continual learningcited by 570
  11. 2020Dataset Condensation with Gradient Matchingcited by 512
  12. 2021Dataset Condensation with Distribution Matchingcited by 363
11 more
  1. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 290
  2. 2020Coresets via Bilevel Optimization for Continual Learning and Streamingcited by 191
  3. 2021Graph Condensation for Graph Neural Networkscited by 150
  4. 2021Scaling Up Graph Neural Networks Via Graph Coarseningcited by 80
  5. 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
  6. 2021Graph Learning based Recommender Systems: A Reviewcited by 59
  7. 2017Automated Scalable Bayesian Inference via Hilbert Coresetscited by 55
  8. 2020ScaIL: Classifier Weights Scaling for Class Incremental Learningcited by 47
  9. 2020Building a PubMed knowledge graphcited by 38
  10. 2021Survey of Image Based Graph Neural Networkscited by 7
  11. 2018Generative Invertible Networks (GIN): Pathophysiology-Interpretable Feature Mapping and Virtual Patient Generationcited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 25; 2025: 13; 2026: 9.

60 papers.

Sort:

  1. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  2. 2023A Comprehensive Survey of Dataset Distillationcited by 114
  3. 2023Data Distillation: A Surveycited by 86
  4. 2022Accelerating Dataset Distillation via Model Augmentationcited by 62
  5. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  6. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  7. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  8. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  9. 2023A Survey on Dataset Distillation: Approaches, Applications and Future Directionscited by 32
  10. 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matchingcited by 28
  11. 2024Graph Condensation: A Surveycited by 23
  12. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
38 more
  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2025Dataset Distillation via Vision-Language Category Prototypecited by 18
  3. 2023Graph Distillation with Eigenbasis Matchingcited by 16
  4. 2023Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Trainingcited by 12
  5. 2024GC-Bench: An Open and Unified Benchmark for Graph Condensationcited by 12
  6. 2024Disentangled Condensation for Large-scale Graphscited by 10
  7. 2023PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensationcited by 9
  8. 2024A Survey on Graph Condensationcited by 9
  9. 2024Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matchingcited by 8
  10. 2024Dataset Condensation for Time Series Classification via Dual Domain Matchingcited by 8
  11. 2024Simple Graph Condensationcited by 8
  12. 2024Graph Continual Learning with Debiased Lossless Memory Replaycited by 8
  13. 2024Federated Graph Condensation with Information Bottleneck Principlescited by 8
  14. 2025GCAL: Adapting Graph Models to Evolving Domain Shiftscited by 8
  15. 2024GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insightscited by 7
  16. 2024CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecastingcited by 6
  17. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  18. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  19. 2024GCondenser: Benchmarking Graph Condensationcited by 5
  20. 2024Backdoor Graph Condensationcited by 5
  21. 2024Calibrated Dataset Condensation for Faster Hyperparameter Searchcited by 4
  22. 2024Bi-Directional Multi-Scale Graph Dataset Condensation via Information Bottleneckcited by 4
  23. 2025Efficient Graph Condensation via Gaussian Processcited by 4
  24. 2024Spectral Greedy Coresets for Graph Neural Networkscited by 3
  25. 2025Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensationcited by 2
  26. 2026Effective Dataset Distillation for Spatio-Temporal Forecasting with Bi-dimensional Compressioncited by 2
  27. 2024GSTAM: Efficient Graph Distillation with Structural Attention-Matchingcited by 1
  28. 2024Training-free Heterogeneous Graph Condensation via Data Selectioncited by 1
  29. 2025Learning hidden cascades via classificationcited by 1
  30. 2025Dynamic Graph Condensationcited by 1
  31. 2025Multi-view Graph Condensation via Tensor Decompositioncited by 1
  32. 2026Analytic Drift Resister for Non-Exemplar Continual Graph Learningcited by 1
  33. 2026Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependencecited by 1
  34. 2023Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matchingcited by 0
  35. 2024Acceleration Algorithms in GNNs: A Surveycited by 0
  36. 2024Graph Sparsification for Enhanced Conformal Prediction in Graph Neural Networkscited by 0
  37. 2024Extending Graph Condensation to Multi-Label Datasets: A Benchmark Studycited by 0
  38. 2025On the Importance of Pretraining Data Alignment for Atomic Property Predictioncited by 0

50 most cited of 60 All 60 (JSON)