Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Towards Subgraph Isomorphism Counting with Graph Kernels (2405.07497v1)

Published 13 May 2024 in cs.LG

Abstract: Subgraph isomorphism counting is known as #P-complete and requires exponential time to find the accurate solution. Utilizing representation learning has been shown as a promising direction to represent substructures and approximate the solution. Graph kernels that implicitly capture the correlations among substructures in diverse graphs have exhibited great discriminative power in graph classification, so we pioneeringly investigate their potential in counting subgraph isomorphisms and further explore the augmentation of kernel capability through various variants, including polynomial and Gaussian kernels. Through comprehensive analysis, we enhance the graph kernels by incorporating neighborhood information. Finally, we present the results of extensive experiments to demonstrate the effectiveness of the enhanced graph kernels and discuss promising directions for future research.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Color-coding. Journal of the ACM, 42(4):844–856, 1995.
  2. Biomolecular network motif counting and discovery by color coding. Bioinformatics, 24(13):i241–i249, 2008.
  3. Gradual weisfeiler-leman: Slow and steady wins the race. In LoG, volume 198 of Proceedings of Machine Learning Research, page 20. PMLR, 2022.
  4. Shortest-path kernels on graphs. In ICDM, pages 74–81, 2005.
  5. Motivo: fast motif counting via succinct color coding and adaptive sampling. PVLDB, 12(11):1651–1663, 2019.
  6. An optimal lower bound on the number of variables for graph identifications. Combinatorica, 12(4):389–410, 1992.
  7. Challenging the time complexity of exact subgraph isomorphism for huge and dense graphs with VF3. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4):804–818, 2018.
  8. Libsvm: a library for support vector machines. Transactions on Intelligent Systems and Technology, 2(3):1–27, 2011.
  9. Can graph neural networks count substructures? In NeurIPS, volume 33, pages 10383–10395, 2020.
  10. Fg-index: towards verification-free query processing on graph databases. In SIGMOD, pages 857–872, 2007.
  11. Applying graph kernels to model-driven engineering problems. In MASES, pages 1–5, 2018.
  12. A (sub)graph isomorphism algorithm for matching large graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(10):1367–1372, 2004a.
  13. A (sub)graph isomorphism algorithm for matching large graphs. Transactions on Pattern Analysis and Machine Intelligence, 26(10):1367–1372, 2004b.
  14. Transformer-xl: Attentive language models beyond a fixed-length context. In ACL, pages 2978–2988, 2019.
  15. Liblinear: A library for large linear classification. Journal of Machine Learning Research, 9:1871–1874, 2008.
  16. Neural message passing for quantum chemistry. In ICML, volume 70, pages 1263–1272, 2017.
  17. Graphgrep: A fast and universal method for querying graphs. In ICPR, pages 112–115, 2002.
  18. Recognizing identical events with graph kernels. In ACL, pages 797–803, 2013.
  19. Turboisoiso{}_{\mbox{iso}}start_FLOATSUBSCRIPT iso end_FLOATSUBSCRIPT: towards ultrafast and robust subgraph isomorphism search in large graph databases. In SIGMOD, pages 337–348, 2013.
  20. Graphs-at-a-time: query language and access methods for graph databases. In SIGMOD, pages 405–418, 2008.
  21. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997.
  22. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1):55–67, 1970.
  23. Meta structure: Computing relevance in large heterogeneous information networks. In SIGKDD, pages 1595–1604, 2016.
  24. Path sampling: A fast and provable method for estimating 4-vertex subgraph counts. In WWW, pages 495–505, 2015.
  25. Topological graph kernel on multiple thresholded functional connectivity networks for mild cognitive impairment classification. Human brain mapping, 35(7):2876–2897, 2014.
  26. Kernels for graph classification. In ICDM workshop, volume 2002, 2002.
  27. Yoon Kim. Convolutional neural networks for sentence classification. In EMNLP, pages 1746–1751, 2014.
  28. CT-index: Fingerprint-based graph indexing combining cycles and trees. In ICDE, pages 1115–1126, 2011.
  29. On valid optimal assignment kernels and applications to graph classification. In NeurIPS, pages 1615–1623, 2016.
  30. GREW-A scalable frequent subgraph discovery algorithm. In ICDM, pages 439–442, 2004.
  31. Deriving neural architectures from sequence and graph kernels. In ICML, volume 70, pages 2024–2033, 2017.
  32. Graph convolutional networks with dual message passing for subgraph isomorphism counting and matching. In AAAI, pages 7594–7602, 2022.
  33. Neural subgraph isomorphism counting. In KDD, pages 1959–1969, 2020.
  34. Network motifs: simple building blocks of complex networks. Science, 298(5594):824–827, 2002.
  35. Weisfeiler and leman go sparse: Towards scalable higher-order graph embeddings. In NeurIPS, 2020.
  36. Exploiting vertex relationships in speeding up subgraph isomorphism over large graphs. PVLDB, 8(5):617–628, 2015.
  37. Pedro Manuel Pinto Ribeiro and Fernando M. A. Silva. Efficient subgraph frequency estimation with g-tries. In WABI, volume 6293, pages 238–249, 2010.
  38. Modeling relational data with graph convolutional networks. In ESWC, volume 10843, pages 593–607, 2018.
  39. Brenda, the enzyme database: updates and major new developments. Nucleic acids research, 32(suppl_1):D431–D433, 2004.
  40. A generalized weisfeiler-lehman graph kernel. Machine Learning, 111(7):2601–2629, 2022.
  41. Multi-task learning for conversational question answering over a large-scale knowledge base. In EMNLP-IJCNLP, pages 2442–2451, 2019.
  42. Efficient graphlet kernels for large graph comparison. In AISTATS, volume 5, pages 488–495, 2009.
  43. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research, 12:2539–2561, 2011.
  44. Pamogk: a pathway graph kernel-based multiomics approach for patient clustering. Bioinformatics, 36(21):5237–5246, 2020.
  45. Julian R. Ullmann. An algorithm for subgraph isomorphism. Journal of the ACM, 23(1):31–42, 1976.
  46. Composition-based multi-relational graph convolutional networks. In ICLR, 2020.
  47. The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series, 2(9):12–16, 1968.
  48. Sebastian Wernicke. A faster algorithm for detecting network motifs. In WABI, volume 3692, pages 165–177, 2005.
  49. How powerful are graph neural networks? In ICLR, 2019.
  50. Graph indexing: A frequent structure-based approach. In SIGMOD, pages 335–346, 2004.
  51. Graph convolutional neural networks for web-scale recommender systems. In SIGKDD, pages 974–983, 2018.
  52. Neural subgraph matching. arXiv preprint arXiv:2007.03092, 2020.
  53. Learning to count isomorphisms with graph neural networks. In AAAI, 2023.
  54. Fast multi-view segment graph kernel for object classification. Signal Processing, 93(6):1597–1607, 2013.
  55. Meta-graph based recommendation fusion over heterogeneous information networks. In SIGKDD, pages 635–644, 2017.
  56. Sahad: Subgraph analysis in massive networks using hadoop. In IPDPS, pages 390–401, 2012.

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