Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 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

A Survey on Graph Condensation (2402.02000v1)

Published 3 Feb 2024 in cs.LG

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Coresets for clustering in graphs of bounded treewidth. In International Conference on Machine Learning, pages 569–579. PMLR, 2020.
  2. A unifying framework for spectrum-preserving graph sparsification and coarsening. Advances in Neural Information Processing Systems, 32, 2019.
  3. Summarizing semantic graphs: a survey. The VLDB journal, 28:295–327, 2019.
  4. Graph coarsening: from scientific computing to machine learning. SeMA Journal, pages 1–37, 2022.
  5. Bridging the gap between spatial and spectral domains: A unified framework for graph neural networks. ACM Computing Surveys, 56(5):1–42, 2023.
  6. K Ch Das. The laplacian spectrum of a graph. Computers & Mathematics with Applications, 48(5-6):715–724, 2004.
  7. Graphzoom: A multi-level spectral approach for accurate and scalable graph embedding. In The International Conference on Learning Representations, 2020.
  8. Graph coarsening via convolution matching for scalable graph neural network training. arXiv preprint arXiv:2312.15520, 2023.
  9. Faster hyperparameter search on graphs via calibrated dataset condensation. In NeurIPS 2022 Workshop: New Frontiers in Graph Learning, 2022.
  10. A comprehensive study on large-scale graph training: Benchmarking and rethinking. Advances in Neural Information Processing Systems, 35:5376–5389, 2022.
  11. Fair graph distillation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  12. Multiple sparse graphs condensation. Knowledge-Based Systems, 278:110904, 2023.
  13. Graph neural architecture search. International Joint Conference on Artificial Intelligence, 2021.
  14. Graph condensation for inductive node representation learning. arXiv preprint arXiv:2307.15967, 2023.
  15. Graph condensation: A survey. arXiv preprint arXiv:2401.11720, 2024.
  16. Understanding pooling in graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  17. A comprehensive survey on graph reduction: Sparsification, coarsening, and condensation. arXiv preprint, 2024.
  18. Scaling up graph neural networks via graph coarsening. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pages 675–684, 2021.
  19. Graph coarsening with preserved spectral properties. In International Conference on Artificial Intelligence and Statistics, pages 4452–4462. PMLR, 2020.
  20. Graph condensation for graph neural networks. In International Conference on Learning Representations, 2021.
  21. Condensing graphs via one-step gradient matching. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022.
  22. Representation learning for dynamic graphs: A survey. The Journal of Machine Learning Research, 21(1):2648–2720, 2020.
  23. Featured graph coarsening with similarity guarantees. In International Conference on Machine Learning. PMLR, 2023.
  24. Unmasking clever hans predictors and assessing what machines really learn. Nature communications, 10(1):1096, 2019.
  25. Attend who is weak: Enhancing graph condensation via cross-free adversarial training. arXiv preprint arXiv:2311.15772, 2023.
  26. Mile: A multi-level framework for scalable graph embedding. In Proceedings of the International AAAI Conference on Web and Social Media, volume 15, pages 361–372, 2021.
  27. Graph summarization methods and applications: A survey. ACM computing surveys (CSUR), 51(3):1–34, 2018.
  28. Graph pooling for graph neural networks: Progress, challenges, and opportunities. arXiv preprint arXiv:2204.07321, 2022.
  29. Graph condensation via receptive field distribution matching. arXiv preprint arXiv:2206.13697, 2022.
  30. Graph condensation via eigenbasis matching. arXiv preprint arXiv:2310.09202, 2023.
  31. Cat: Balanced continual graph learning with graph condensation. arXiv preprint arXiv:2309.09455, 2023.
  32. Andreas Loukas. Graph reduction with spectral and cut guarantees. J. Mach. Learn. Res., 20(116):1–42, 2019.
  33. Learning to drop: Robust graph neural network via topological denoising. In Proceedings of the 14th ACM international conference on web search and data mining, pages 779–787, 2021.
  34. Unsupervised learning of graph hierarchical abstractions with differentiable coarsening and optimal transport. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 8856–8864, 2021.
  35. Is homophily a necessity for graph neural networks? In International Conference on Learning Representations, 2021.
  36. Gcare: Mitigating subgroup unfairness in graph condensation through adversarial regularization. Applied Sciences, 13(16):9166, 2023.
  37. Subgraph mining in a large graph: A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(4):e1454, 2022.
  38. Fedgkd: Unleashing the power of collaboration in federated graph neural networks. In NeurIPS 2023 Workshop: New Frontiers in Graph Learning, 2023.
  39. Little Ball of Fur: A Python Library for Graph Sampling. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM ’20), page 3133–3140. ACM, 2020.
  40. Curgraph: Curriculum learning for graph classification. In Proceedings of the Web Conference 2021, pages 1238–1248, 2021.
  41. Fast graph condensation with structure-based neural tangent kernel. arXiv preprint arXiv:2310.11046, 2023.
  42. Clnode: Curriculum learning for node classification. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pages 670–678, 2023.
  43. Better with less: A data-active perspective on pre-training graph neural networks. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  44. Kernel ridge regression-based graph dataset distillation. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023.
  45. Does graph distillation see like vision dataset counterpart? In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  46. Dataset distillation: A comprehensive review. arXiv preprint arXiv:2301.07014, 2023.
  47. Dataset condensation with gradient matching. arXiv preprint arXiv:2006.05929, 2020.
  48. Graphsmote: Imbalanced node classification on graphs with graph neural networks. In Proceedings of the 14th ACM international conference on web search and data mining, pages 833–841, 2021.
  49. Structure-free graph condensation: From large-scale graphs to condensed graph-free data. arXiv preprint arXiv:2306.02664, 2023.
Citations (8)
View on Semantic Scholar

Summary

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

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

Tweets