Document Open Access Logo

Recovering Communities in Structured Random Graphs

Authors Michael Kapralov , Luca Trevisan, Weronika Wrzos-Kaminska

PDF

File

Thumbnail PDF
PDF
LIPIcs.ITCS.2026.85.pdf
  • Filesize: 0.81 MB
  • 23 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Theory of computation → Graph algorithms analysis
  • Mathematics of computing → Random graphs
Keywords
  • Hypercube graphs
  • Community detection
  • Fourier analysis of Boolean functions

Metrics

Abstract

The problem of recovering planted community structure in random graphs has received a lot of attention in the literature on the stochastic block model, where the input is a random graph in which edges crossing between different communities appear with smaller probability than edges induced by communities. The communities themselves form a collection of vertex-disjoint sparse cuts in the expected graph, and can be recovered, often exactly, from a sample as long as a separation condition on the intra- and inter-community edge probabilities is satisfied. 
In this paper, we ask whether the presence of a large number of overlapping sparsest cuts in the expected graph still allows recovery. For example, the d-dimensional hypercube graph admits d distinct (balanced) sparsest cuts, one for every coordinate. Can these cuts be identified given a random sample of the edges of the hypercube where each edge is present independently with some probability p ∈ (0, 1)? We show that this is the case, in a very strong sense: the sparsest balanced cut in a sample of the hypercube at rate p = Clog d/d for a sufficiently large constant C is 1/poly(d)-close to a coordinate cut with high probability. This is asymptotically optimal and allows approximate recovery of all d cuts simultaneously. Furthermore, for an appropriate sample of hypercube-like graphs recovery can be made exact. The proof is essentially a strong hypercube cut sparsification bound that combines a theorem of Friedgut, Kalai and Naor on boolean functions whose Fourier transform concentrates on the first level of the Fourier spectrum with Karger’s cut counting argument.

Cite As Get BibTex

Michael Kapralov, Luca Trevisan, and Weronika Wrzos-Kaminska. Recovering Communities in Structured Random Graphs. In 17th Innovations in Theoretical Computer Science Conference (ITCS 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 362, pp. 85:1-85:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026) https://doi.org/10.4230/LIPIcs.ITCS.2026.85

Author Details

Michael Kapralov
  • EPFL, Lausanne, Switzerland
Luca Trevisan
  • Bocconi University, Milan, Italy
Weronika Wrzos-Kaminska
  • EPFL, Lausanne, Switzerland

References

  1. Emmanuel Abbe. Community detection and stochastic block models: recent developments. J. Mach. Learn. Res., 18(1):6446-6531, January 2017. Google Scholar
  2. Emmanuel Abbe, François Baccelli, and Abishek Sankararaman. Community detection on euclidean random graphs. Information and Inference: A Journal of the IMA, 10(1):109-160, May 2020. Google Scholar
  3. Emmanuel Abbe, Afonso S. Bandeira, and Georgina Hall. Exact recovery in the stochastic block model. IEEE Transactions on Information Theory, 62(1):471-487, 2016. URL: https://doi.org/10.1109/TIT.2015.2490670.
  4. Emmanuel Abbe, Enric Boix-Adserà, Peter Ralli, and Colin Sandon. Graph powering and spectral robustness. SIAM Journal on Mathematics of Data Science, 2(1):132-157, 2020. URL: https://doi.org/10.1137/19M1257135.
  5. Emmanuel Abbe and Colin Sandon. Community detection in general stochastic block models: Fundamental limits and efficient algorithms for recovery. In Proceedings of the 2015 IEEE 56th Annual Symposium on Foundations of Computer Science (FOCS), FOCS '15, pages 670-688, USA, 2015. IEEE Computer Society. URL: https://doi.org/10.1109/FOCS.2015.47.
  6. Luiz Emilio Allem, K. Avrachenkov, Carlos Hoppen, Hariprasad Manjunath, and Lucas Sibemberg. Multi-community spectral clustering for geometric graphs, 2025. URL: https://doi.org/10.48550/arXiv.2508.00893.
  7. Sanjeev Arora, Rong Ge, Sushant Sachdeva, and Grant Schoenebeck. Finding overlapping communities in social networks: toward a rigorous approach. In Proceedings of the 13th ACM Conference on Electronic Commerce, EC '12, pages 37-54, New York, NY, USA, 2012. Association for Computing Machinery. URL: https://doi.org/10.1145/2229012.2229020.
  8. Konstantin Avrachenkov, Andrei Bobu, and Maximilien Dreveton. Higher-order spectral clustering for geometric graphs. Journal of Fourier Analysis and Applications, 27(2):22, 2021. Google Scholar
  9. Kiril Bangachev and Guy Bresler. Sandwiching random geometric graphs and erdos-renyi with applications: Sharp thresholds, robust testing, and enumeration. In Proceedings of the 57th Annual ACM Symposium on Theory of Computing, pages 310-321, June 2025. URL: https://doi.org/10.1145/3717823.3718125.
  10. Charles Bordenave, Marc Lelarge, and Laurent Massoulié. Non-backtracking spectrum of random graphs: Community detection and non-regular ramanujan graphs. In Venkatesan Guruswami, editor, IEEE 56th Annual Symposium on Foundations of Computer Science, FOCS 2015, Berkeley, CA, USA, 17-20 October, 2015, pages 1347-1357. IEEE Computer Society, 2015. URL: https://doi.org/10.1109/FOCS.2015.86.
  11. Sébastien Bubeck, Jian Ding, Ronen Eldan, and Miklós Z. Rácz. Testing for high‐dimensional geometry in random graphs. Random Structures & Algorithms, 49, 2014. URL: https://api.semanticscholar.org/CorpusID:15367951.
  12. Yudong Chen and Jiaming Xu. Statistical-computational tradeoffs in planted problems and submatrix localization with a growing number of clusters and submatrices. J. Mach. Learn. Res., 17(1):882-938, January 2016. Google Scholar
  13. Ashish Chiplunkar, Michael Kapralov, Sanjeev Khanna, Aida Mousavifar, and Yuval Peres. Testing graph clusterability: Algorithms and lower bounds. In 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS), pages 497-508. IEEE, 2018. URL: https://doi.org/10.1109/FOCS.2018.00054.
  14. Anne Condon and Richard M. Karp. Algorithms for graph partitioning on the planted partition model. Random Structures & Algorithms, 18(2):116-140, 2001. URL: https://doi.org/10.1002/1098-2418(200103)18:2<116::AID-RSA1001>3.0.CO;2-2.
  15. Artur Czumaj, Pan Peng, and Christian Sohler. Testing cluster structure of graphs. In Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing, STOC '15, pages 723-732, New York, NY, USA, 2015. Association for Computing Machinery. URL: https://doi.org/10.1145/2746539.2746618.
  16. Aurelien Decelle, Florent Krzakala, Cristopher Moore, and Lenka Zdeborová. Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications. Phys. Rev. E, 84:066106, December 2011. URL: https://doi.org/10.1103/PhysRevE.84.066106.
  17. Benjamin Doerr. Probabilistic Tools for the Analysis of Randomized Optimization Heuristics, pages 1-87. Springer International Publishing, January 2020. URL: https://doi.org/10.1007/978-3-030-29414-4_1.
  18. Ehud Friedgut, Gil Kalai, and Assaf Naor. Boolean functions whose fourier transform is concentrated on the first two levels. Advances in Applied Mathematics, 29(3):427-437, 2002. URL: https://doi.org/10.1016/S0196-8858(02)00024-6.
  19. Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, and Barna Saha. The geometric block model. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), April 2018. URL: https://doi.org/10.1609/aaai.v32i1.11905.
  20. Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, and Barna Saha. Connectivity of Random Annulus Graphs and the Geometric Block Model. In Dimitris Achlioptas and László A. Végh, editors, Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2019), volume 145 of Leibniz International Proceedings in Informatics (LIPIcs), pages 53:1-53:23, Dagstuhl, Germany, 2019. Schloss Dagstuhl - Leibniz-Zentrum für Informatik. URL: https://doi.org/10.4230/LIPIcs.APPROX-RANDOM.2019.53.
  21. Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, and Barna Saha. Community recovery in the geometric block model. J. Mach. Learn. Res., 24(1), January 2023. URL: http://jmlr.org/papers/v24/22-0572.html.
  22. Julia Gaudio, Xiaochun Niu, and Ermin Wei. Exact community recovery in the geometric sbm. In Proceedings of the 2024 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 2158-2184, 2024. URL: https://doi.org/10.1137/1.9781611977912.78.
  23. Grzegorz Gluch, Michael Kapralov, Silvio Lattanzi, Aida Mousavifar, and Christian Sohler. Spectral clustering oracles in sublinear time. In Proceedings of the 2021 ACM-SIAM Symposium on Discrete Algorithms, SODA 2021, Virtual Conference, January 10 - 13, 2021, pages 1598-1617. SIAM, 2021. URL: https://doi.org/10.1137/1.9781611976465.97.
  24. Paul Holland, Kathryn B. Laskey, and Samuel Leinhardt. Stochastic blockmodels: First steps. Social Networks, 5:109-137, 1983. URL: https://api.semanticscholar.org/CorpusID:34098453.
  25. David R Karger. Global min-cuts in RNC, and other ramifications of a simple min-cut algorithm. In ACM-SIAM Symposium on Discrete Algorithms, 1993. URL: https://api.semanticscholar.org/CorpusID:10445344.
  26. Shuangping Li and Tselil Schramm. Spectral clustering in the gaussian mixture block model, 2023. URL: https://doi.org/10.48550/arXiv.2305.00979.
  27. Siqi Liu, Sidhanth Mohanty, Tselil Schramm, and Elizabeth Yang. Testing thresholds for high-dimensional sparse random geometric graphs. In Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing, STOC 2022, pages 672-677, New York, NY, USA, 2022. Association for Computing Machinery. URL: https://doi.org/10.1145/3519935.3519989.
  28. Florence Jessie MacWilliams and Neil James Alexander Sloane. The theory of error-correcting codes, volume 16. Elsevier, 1977. Google Scholar
  29. Laurent Massoulié. Community detection thresholds and the weak ramanujan property. In Proceedings of the Forty-Sixth Annual ACM Symposium on Theory of Computing, STOC '14, pages 694-703, New York, NY, USA, 2014. Association for Computing Machinery. URL: https://doi.org/10.1145/2591796.2591857.
  30. F. McSherry. Spectral partitioning of random graphs. In Proceedings 42nd IEEE Symposium on Foundations of Computer Science, pages 529-537, 2001. URL: https://doi.org/10.1109/SFCS.2001.959929.
  31. Elchanan Mossel, Joe Neeman, and Allan Sly. Reconstruction and estimation in the planted partition model. Probability Theory and Related Fields, 162, July 2014. URL: https://doi.org/10.1007/s00440-014-0576-6.
  32. Elchanan Mossel, Joe Neeman, and Allan Sly. Consistency thresholds for the planted bisection model. In Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing, STOC '15, pages 69-75, New York, NY, USA, 2015. Association for Computing Machinery. URL: https://doi.org/10.1145/2746539.2746603.
  33. Ryan O’Donnell. Analysis of Boolean Functions. Cambridge University Press, 2014. Google Scholar
  34. Abishek Sankararaman and François Baccelli. Community detection on euclidean random graphs. In Proceedings of the 2018 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), 2018. URL: https://arxiv.org/abs/https://epubs.siam.org/doi/pdf/10.1137/1.9781611975031.142.
  35. van Vu. A simple svd algorithm for finding hidden partitions. Combinatorics, Probability and Computing, 27:124-140, 2014. URL: https://api.semanticscholar.org/CorpusID:8561244.
  36. Douglas Brent West et al. Introduction to graph theory, volume 2. Prentice hall Upper Saddle River, 2001. Google Scholar
  37. Yuan Zhang, Elizaveta Levina, and Ji Zhu. Detecting overlapping communities in networks using spectral methods. SIAM Journal on Mathematics of Data Science, 2(2):265-283, 2020. URL: https://doi.org/10.1137/19M1272238.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2025 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact