mlsanityData to 14 Oct 2026

RobGC: Towards Robust Graph Condensation

arXiv 2406.13200 ↗First posted 19 Jun 2024cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have attracted widespread attention for their impressive capability of graph representation learning. However, the increasing prevalence of large-scale graphs presents a significant challenge for GNN training due to their computational demands, limiting the applicability of GNNs in various scenarios. In response to this challenge, graph condensation (GC) is proposed as a promising acceleration solution, focusing on generating an informative compact graph that enables efficient training of GNNs while retaining performance. Despite the potential to accelerate GNN training, existing GC methods overlook the quality of large training graphs during both the training and inference stages. They indiscriminately emulate the training graph distributions, making the condensed graphs susceptible to noises within the training graph and significantly impeding the application of GC in intricate real-world scenarios. To address this issue, we propose robust graph condensation (RobGC), a plug-and-play approach for GC to extend the robustness and applicability of condensed graphs in noisy graph structure environments. Specifically, RobGC leverages the condensed graph as a feedback signal to guide the denoising process on the original training graph. A label propagation-based alternating optimization strategy is in place for the condensation and denoising processes, contributing to the mutual purification of the condensed graph and training graph. Additionally, as a GC method designed for inductive graph inference, RobGC facilitates test-time graph denoising by leveraging the noise-free condensed graph to calibrate the structure of the test graph. Extensive experiments show that RobGC is compatible with various GC methods, significantly boosting their robustness under different types and levels of graph structural noises.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 51 of its 72 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

51 of 72 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  7. 2018Link Prediction Based on Graph Neural Networkscited by 832
  8. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  10. 2021Dataset Condensation with Distribution Matchingcited by 365
  11. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  12. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
38 more
  1. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  2. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  3. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  4. 2021Graph Condensation for Graph Neural Networkscited by 150
  5. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  6. 2023A Comprehensive Survey of Dataset Distillationcited by 115
  7. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  8. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  9. 2021Robustness of Graph Neural Networks at Scalecited by 100
  10. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  11. 2023Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Datacited by 71
  12. 2019Graph-Revised Convolutional Networkcited by 59
  13. 2022XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendationcited by 57
  14. 2024A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensationcited by 57
  15. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  16. 2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 51
  17. 2022Graph-based Molecular Representation Learningcited by 51
  18. 2023Does Graph Distillation See Like Vision Dataset Counterpart?cited by 45
  19. 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
  20. 2022PaSca: a Graph Neural Architecture Search System under the Scalable Paradigmcited by 37
  21. 2023Fast Graph Condensation with Structure-based Neural Tangent Kernelcited by 36
  22. 2018Robust Graph Learning from Noisy Datacited by 34
  23. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  24. 2023Graph Condensation for Inductive Node Representation Learningcited by 31
  25. 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matchingcited by 28
  26. 2024Graph Condensation: A Surveycited by 23
  27. 2024Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partitioncited by 23
  28. 2021Training Robust Graph Neural Networks with Topology Adaptive Edge Droppingcited by 20
  29. 2024Graph Data Condensation via Self-expressive Graph Structure Reconstructioncited by 18
  30. 2023Graph Distillation with Eigenbasis Matchingcited by 16
  31. 2019A Quest for Structure: Jointly Learning the Graph Structure and Semi-Supervised Classificationcited by 13
  32. 2024Challenging Low Homophily in Social Recommendationcited by 10
  33. 2023Semantic-aware Node Synthesis for Imbalanced Heterogeneous Information Networkscited by 9
  34. 2024A Survey on Graph Condensationcited by 9
  35. 2024Graph Condensation for Open-World Graph Learningcited by 9
  36. 2022Time-aware Dynamic Graph Embedding for Asynchronous Structural Evolutioncited by 8
  37. 2023Accelerating Scalable Graph Neural Network Inference with Node-Adaptive Propagationcited by 8
  38. 2024Simple Graph Condensationcited by 8

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 4.

8 papers.

  1. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  2. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  3. 2024Training-free Heterogeneous Graph Condensation via Data Selectioncited by 1
  4. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  5. 2025Adaptive Graph Coarsening for Efficient GNN Trainingcited by 0
  6. 2026FairGC: Fairness-aware Graph Condensationcited by 0
  7. 2026Model-to-Data Distillation for Graph Neural Networkscited by 0
  8. 2026Heterogeneous Graph Condensation via Role-Aware Clusteringcited by 0