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

On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters (2309.17053v3)

Published 29 Sep 2023 in cs.LG

Abstract: Seminal research in the field of graph neural networks (GNNs) has revealed a direct correspondence between the expressive capabilities of GNNs and the $k$-dimensional Weisfeiler-Leman ($k$WL) test, a widely-recognized method for verifying graph isomorphism. This connection has reignited interest in comprehending the specific graph properties effectively distinguishable by the $k$WL test. A central focus of research in this field revolves around determining the least dimensionality $k$, for which $k$WL can discern graphs with different number of occurrences of a pattern graph $P$. We refer to such a least $k$ as the WL-dimension of this pattern counting problem. This inquiry traditionally delves into two distinct counting problems related to patterns: subgraph counting and induced subgraph counting. Intriguingly, despite their initial appearance as separate challenges with seemingly divergent approaches, both of these problems are interconnected components of a more comprehensive problem: "graph motif parameters". In this paper, we provide a precise characterization of the WL-dimension of labeled graph motif parameters. As specific instances of this result, we obtain characterizations of the WL-dimension of the subgraph counting and induced subgraph counting problem for every labeled pattern $P$. We additionally demonstrate that in cases where the $k$WL test distinguishes between graphs with varying occurrences of a pattern $P$, the exact number of occurrences of $P$ can be computed uniformly using only local information of the last layer of a corresponding GNN. We finally delve into the challenge of recognizing the WL-dimension of various graph parameters. We give a polynomial time algorithm for determining the WL-dimension of the subgraph counting problem for given pattern $P$, answering an open question from previous work.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Biomolecular network motif counting and discovery by color coding. Bioinformatics, 13:1–24, 2008.
  2. On weisfeiler-leman invariance: Subgraph counts and related graph properties. J. Comput. Syst. Sci., 113:42–59, 2020.
  3. Graph neural networks with local graph parameters. In NeurIPS 2021, pp.  25280–25293, 2021.
  4. Weisfeiler and leman go relational. In LoG, volume 198 of Proceedings of Machine Learning Research, pp.  46. PMLR, 2022.
  5. Hans L. Bodlaender. A linear-time algorithm for finding tree-decompositions of small treewidth. SIAM J. Comput., 25(6):1305–1317, 1996. doi: 10.1137/S0097539793251219.
  6. Improving graph neural network expressivity via subgraph isomorphism counting. IEEE Trans. Pattern Anal. Mach. Intell., 45(1):657–668, 2023.
  7. Counting graphlets: Space vs time. In WSDM, pp.  557–566. ACM, 2017. doi: 10.1145/3018661.3018732.
  8. An optimal lower bound on the number of variables for graph identification. Comb., 12(4):389–410, 1992.
  9. Counting answers to existential positive queries: A complexity classification. In Proc. PODS, pp.  315–326. ACM, 2016. doi: 10.1145/2902251.2902279. URL https://doi.org/10.1145/2902251.2902279.
  10. Can graph neural networks count substructures? In NeurIPS, 2020.
  11. Bruno Courcelle. The monadic second-order logic of graphs. i. recognizable sets of finite graphs. Inf. Comput., 85(1):12–75, 1990.
  12. Homomorphisms are a good basis for counting small subgraphs. In STOC, pp.  210–223. ACM, 2017.
  13. Learning combinatorial optimization algorithms over graphs. In ICML, 2021.
  14. Message passing for query answering over knowledge graphs. CoRR, abs/2002.02406, 2020. URL https://arxiv.org/abs/2002.02406.
  15. Lovász meets weisfeiler and leman. In Proc. ICALP, volume 107 of LIPIcs, pp. 40:1–40:14. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2018. doi: 10.4230/LIPIcs.ICALP.2018.40.
  16. Counting answers to existential questions. In Proc. ICALP 2019, volume 132 of LIPIcs, pp. 113:1–113:15. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2019.
  17. Reinhard Diestel. Graph Theory, 4th Edition, volume 173 of Graduate texts in mathematics. Springer, 2012.
  18. Zdenek Dvorák. On recognizing graphs by numbers of homomorphisms. J. Graph Theory, 64(4):330–342, 2010. doi: 10.1002/jgt.20461.
  19. A fair comparison of graph neural networks for graph classification. In ICLR, 2020.
  20. Martin Fürer. On the combinatorial power of the weisfeiler-lehman algorithm. CoRR, abs/1704.01023, 2017. URL http://arxiv.org/abs/1704.01023.
  21. Inductive logical query answering in knowledge graphs. In NeurIPS, 2022.
  22. Neural message passing for quantum chemistry. In ICML, 2017.
  23. The weisfeiler-leman dimension of existential conjunctive queries. 2024.
  24. Pebble games and linear equations. J. Symb. Log., 80(3):797–844, 2015.
  25. Knowledge graphs. ACM Comput. Surv., 54(4):71:1–71:37, 2022.
  26. A theory of link prediction via relational weisfeiler-leman. CoRR, abs/2302.02209, 2023.
  27. Network global testing by counting graphlets. In ICML, volume 80, pp.  2338–2346. PMLR, 2018. URL http://proceedings.mlr.press/v80/jin18b.html.
  28. Jakob Jonsson. Simplicial complexes of graphs, volume 3. Springer, 2008.
  29. A comprehensive survey on graph neural networks. IEEE Communications Surveys & Tutorials, 2020.
  30. Community detection in graphs with graphsage. In ICLR, 2018. URL https://arxiv.org/abs/1706.02216.
  31. A property testing framework for the theoretical expressivity of graph kernels. In IJCAI, pp.  2348–2354. ijcai.org, 2018.
  32. László Lovász. Operations with structures. Acta Mathematica Hungarica, 18(3-4):321–328, 1967.
  33. Encoding sentences with graph convolutional networks for semantic role labeling. In EMNLP, 2017.
  34. Weisfeiler and leman go neural: Higher-order graph neural networks. In AAAI, pp.  4602–4609, 2019.
  35. Weisfeiler and leman go sparse: Towards scalable higher-order graph embeddings. In NeurIPS 2020, 2020.
  36. Daniel Neuen. Homomorphism-distinguishing closedness for graphs of bounded tree-width. CoRR, abs/2304.07011, 2023.
  37. OEIS Foundation Inc. The On-Line Encyclopedia of Integer Sequences, 2023. Published electronically at http://oeis.org.
  38. From local measurements to network spectral properties: Beyond degree distributions. In CDC, pp.  2686–2691. IEEE, 2010.
  39. David E. Roberson. Oddomorphisms and homomorphism indistinguishability over graphs of bounded degree. CoRR, abs/2206.10321, 2022.
  40. Graph minors. XX. wagner’s conjecture. J. Comb. Theory, Ser. B, 92(2):325–357, 2004. doi: 10.1016/j.jctb.2004.08.001.
  41. Marc Roth. Counting problems on quantum graphs: Parameterized and exact complexity classifications, 2019.
  42. Counting induced subgraphs: A topological approach to #w[1]-hardness. Algorithmica, 82(8):2267–2291, 2020.
  43. Modeling relational data with graph convolutional networks. In ESWC, 2018.
  44. Tim Seppelt. Logical equivalences, homomorphism indistinguishability, and forbidden minors. CoRR, abs/2302.11290, 2023.
  45. Efficient graphlet kernels for large graph comparison. In AISTATS, volume 5 of JMLR Proceedings, 2009.
  46. Inductive relation prediction by subgraph reasoning. In ICML, pp.  9448–9457, 2020.
  47. The reduction of a graph to canonical form and the algebra which appears therein, 1968.
  48. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021.
  49. Graph neural networks in node classification: survey and evaluation. Mach. Vis. Appl., 33(1):4, 2022.
  50. How powerful are graph neural networks? In ICLR, 2019.
  51. Graph convolutional neural networks for web-scale recommender systems. In KDD, 2018.
  52. Graph neural networks: A review of methods and applications. AI Open, 2020.
  53. Neural bellman-ford networks: A general graph neural network framework for link prediction. In NeurIPS 2021, pp.  29476–29490, 2021.
Citations (7)
View on Semantic Scholar

Summary

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

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