Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Graph Condensation: A Survey (2401.11720v2)

Published 22 Jan 2024 in cs.LG and cs.AI

Abstract: The rapid growth of graph data poses significant challenges in storage, transmission, and particularly the training of graph neural networks (GNNs). To address these challenges, graph condensation (GC) has emerged as an innovative solution. GC focuses on synthesizing a compact yet highly representative graph, enabling GNNs trained on it to achieve performance comparable to those trained on the original large graph. The notable efficacy of GC and its broad prospects have garnered significant attention and spurred extensive research. This survey paper provides an up-to-date and systematic overview of GC, organizing existing research into five categories aligned with critical GC evaluation criteria: effectiveness, generalization, efficiency, fairness, and robustness. To facilitate an in-depth and comprehensive understanding of GC, this paper examines various methods under each category and thoroughly discusses two essential components within GC: optimization strategies and condensed graph generation. We also empirically compare and analyze representative GC methods with diverse optimization strategies based on the five proposed GC evaluation criteria. Finally, we explore the applications of GC in various fields, outline the related open-source libraries, and highlight the present challenges and novel insights, with the aim of promoting advancements in future research. The related resources can be found at https://github.com/XYGaoG/Graph-Condensation-Papers.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Graph based anomaly detection and description: a survey. Data mining and knowledge discovery, 29:626–688, 2015.
  2. Anonymous. CTRL: Graph condensation via crafting rational trajectory matching. In Openview, 2023.
  3. Digraphs: theory, algorithms and applications. Springer Science & Business Media, 2008.
  4. A survey on spectral graph neural networks. arXiv preprint arXiv:2302.05631, 2023.
  5. An entity event knowledge graph for human resources management in public administration: the case of education personnel. In 2023 IEEE 25th Conference on Business Informatics (CBI), pages 1–8. IEEE, 2023.
  6. A unifying framework for spectrum-preserving graph sparsification and coarsening. Advances in Neural Information Processing Systems, 32, 2019.
  7. Dataset distillation by matching training trajectories. In CVPR, pages 4750–4759, 2022.
  8. Faster hyperparameter search for GNNs via calibrated dataset condensation. arXiv, 2022.
  9. Graph neural tangent kernel: Fusing graph neural networks with graph kernels. In NeurIPS, 2019.
  10. Graph lifelong learning: A survey. IEEE Computational Intelligence Magazine, 18(1):32–51, 2023.
  11. Fair graph distillation. In NeurIPS, 2023.
  12. Federated graph machine learning: A survey of concepts, techniques, and applications. ACM SIGKDD Explorations Newsletter, 24(2):32–47, 2022.
  13. Multiple sparse graphs condensation. Knowledge-Based Systems, 2023.
  14. Graph neural architecture search. In International joint conference on artificial intelligence. International Joint Conference on Artificial Intelligence, 2021.
  15. Semantic-aware node synthesis for imbalanced heterogeneous information networks. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 545–555, 2023.
  16. Accelerating scalable graph neural network inference with node-adaptive propagation. arXiv preprint arXiv:2310.10998, 2023.
  17. Graph condensation for inductive node representation learning. In ICDE, 2024.
  18. A survey on dataset distillation: Approaches, applications and future directions. In IJCAI, 2023.
  19. A kernel two-sample test. JMLR, 2012.
  20. Graph-based molecular representation learning. arXiv preprint arXiv:2207.04869, 2022.
  21. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 1024–1034, 2017.
  22. Condensing graphs via one-step gradient matching. In SIGKDD, 2022.
  23. Graph condensation for graph neural networks. In ICLR, 2022.
  24. Irie: Scalable and robust influence maximization in social networks. In 2012 IEEE 12th International Conference on Data Mining, pages 918–923. IEEE, 2012.
  25. Representation learning for dynamic graphs: A survey. The Journal of Machine Learning Research, 21(1):2648–2720, 2020.
  26. Link prediction techniques, applications, and performance: A survey. Physica A: Statistical Mechanics and its Applications, 553:124289, 2020.
  27. A comprehensive survey of dataset distillation. TPAMI, 2024.
  28. Knowledge mining and social dangerousness assessment in criminal justice: metaheuristic integration of machine learning and graph-based inference. Artificial Intelligence and Law, 31(4):653–702, 2023.
  29. Influence maximization on social graphs: A survey. IEEE Transactions on Knowledge and Data Engineering, 30(10):1852–1872, 2018.
  30. Attend who is weak: Enhancing graph condensation via cross-free adversarial training. arXiv, 2023.
  31. Graph condensation via receptive field distribution matching. arXiv, 2022.
  32. Graph condensation via eigenbasis matching. arXiv, 2023.
  33. CaT: Balanced continual graph learning with graph condensation. In ICDM, 2023.
  34. PUMA: Efficient continual graph learning with graph condensation. arXiv, 2023.
  35. Spectrally approximating large graphs with smaller graphs. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, 2018.
  36. The concrete distribution: A continuous relaxation of discrete random variables. In ICLR, 2016.
  37. GCARe: Mitigating subgroup unfairness in graph condensation through adversarial regularization. Applied Sciences, 2023.
  38. A survey on bias and fairness in machine learning. ACM computing surveys (CSUR), 2021.
  39. Dataset meta-learning from kernel ridge-regression. In ICLR, 2020.
  40. Graph neural architecture search: A survey. Tsinghua Science and Technology, 27(4):692–708, 2021.
  41. FedGKD: Unleashing the power of collaboration in federated graph neural networks. arXiv, 2023.
  42. Graph neural networks for intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems, 2023.
  43. Data distillation: A survey. TMLR, 2023.
  44. Infinite recommendation networks: A data-centric approach. Advances in Neural Information Processing Systems, 35:31292–31305, 2022.
  45. A comprehensive survey on graph summarization with graph neural networks. IEEE Transactions on Artificial Intelligence, 2024.
  46. Graph sparsification by effective resistances. In Proceedings of the fortieth annual ACM symposium on Theory of computing, pages 563–568, 2008.
  47. Adversarial attack and defense on graph data: A survey. IEEE Transactions on Knowledge and Data Engineering, 2022.
  48. Recent advances on graph analytics and its applications in healthcare. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 3545–3546, 2020.
  49. A review on graph neural network methods in financial applications. arXiv preprint arXiv:2111.15367, 2021.
  50. Fast graph condensation with structure-based neural tangent kernel. arXiv, 2023.
  51. Simplifying graph convolutional networks. In ICML, 2019.
  52. Graph neural networks in recommender systems: a survey. ACM Computing Surveys, 55(5):1–37, 2022.
  53. Graph learning: A survey. IEEE Transactions on Artificial Intelligence, 2(2):109–127, 2021.
  54. Kernel ridge regression-based graph dataset distillation. In SIGKDD, 2023.
  55. Does graph distillation see like vision dataset counterpart? In NeurIPS, 2023.
  56. Data-centric graph learning: A survey. arXiv, 2023.
  57. Self-supervised learning for recommender systems: A survey. IEEE Transactions on Knowledge and Data Engineering, 2023.
  58. Dataset distillation: A comprehensive review. TPAMI, 2023.
  59. Explainability in graph neural networks: A taxonomic survey. IEEE transactions on pattern analysis and machine intelligence, 45(5):5782–5799, 2022.
  60. A survey on graph neural network acceleration: Algorithms, systems, and customized hardware. arXiv, 2023.
  61. Bo Zhao and Hakan Bilen. Dataset condensation with distribution matching. In WACV, 2023.
  62. Dataset condensation with gradient matching. In ICLR, 2020.
  63. Graph neural networks for graphs with heterophily: A survey. arXiv preprint arXiv:2202.07082, 2022.
  64. Automl for deep recommender systems: A survey. ACM Transactions on Information Systems, 41(4):1–38, 2023.
  65. Towards data-centric graph machine learning: Review and outlook. arXiv, 2023.
  66. Structure-free graph condensation: From large-scale graphs to condensed graph-free data. In NeurIPS, 2023.
  67. Interpreting and unifying graph neural networks with an optimization framework. In Proceedings of the Web Conference 2021, pages 1215–1226, 2021.
  68. A survey on deep graph generation: Methods and applications. In Learning on Graphs Conference, pages 47–1. PMLR, 2022.
Citations (14)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now