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

Partial recovery and weak consistency in the non-uniform hypergraph Stochastic Block Model (2112.11671v3)

Published 22 Dec 2021 in math.ST, math.PR, stat.ML, and stat.TH

Abstract: We consider the community detection problem in sparse random hypergraphs under the non-uniform hypergraph stochastic block model (HSBM), a general model of random networks with community structure and higher-order interactions. When the random hypergraph has bounded expected degrees, we provide a spectral algorithm that outputs a partition with at least a $\gamma$ fraction of the vertices classified correctly, where $\gamma\in (0.5,1)$ depends on the signal-to-noise ratio (SNR) of the model. When the SNR grows slowly as the number of vertices goes to infinity, our algorithm achieves weak consistency, which improves the previous results in Ghoshdastidar and Dukkipati (2017) for non-uniform HSBMs. Our spectral algorithm consists of three major steps: (1) Hyperedge selection: select hyperedges of certain sizes to provide the maximal signal-to-noise ratio for the induced sub-hypergraph; (2) Spectral partition: construct a regularized adjacency matrix and obtain an approximate partition based on singular vectors; (3) Correction and merging: incorporate the hyperedge information from adjacency tensors to upgrade the error rate guarantee. The theoretical analysis of our algorithm relies on the concentration and regularization of the adjacency matrix for sparse non-uniform random hypergraphs, which can be of independent interest.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (80)
  1. Emmanuel Abbe. Community detection and stochastic block models: Recent developments. Journal of Machine Learning Research, 18(177):1–86, 2018.
  2. Exact recovery in the stochastic block model. IEEE Transactions on Information Theory, 62(1):471–487, 2016.
  3. Entrywise eigenvector analysis of random matrices with low expected rank. Annals of statistics, 48(3):1452, 2020.
  4. Community detection in general stochastic block models: Fundamental limits and efficient algorithms for recovery. In 2015 IEEE 56th Annual Symposium on Foundations of Computer Science, pages 670–688. IEEE, 2015.
  5. Proof of the achievability conjectures for the general stochastic block model. Communications on Pure and Applied Mathematics, 71(7):1334–1406, 2018.
  6. Community recovery in hypergraphs. In Communication, Control, and Computing (Allerton), 2016 54th Annual Allerton Conference on, pages 657–663. IEEE, 2016.
  7. Hypergraph spectral clustering in the weighted stochastic block model. IEEE Journal of Selected Topics in Signal Processing, 12(5):959–974, 2018.
  8. Multilayer hypergraph clustering using the aggregate similarity matrix. pages 83–98, 2023.
  9. Spectral detection on sparse hypergraphs. In Communication, Control, and Computing (Allerton), 2015 53rd Annual Allerton Conference on, pages 66–73. IEEE, 2015.
  10. Networks beyond pairwise interactions: structure and dynamics. Physics Reports, 874:1–92, 2020.
  11. Higher-order organization of complex networks. Science, 353(6295):163–166, 2016.
  12. Nonbacktracking spectrum of random graphs: Community detection and nonregular Ramanujan graphs. Annals of probability, 46(1):1–71, 2018.
  13. Music recommendation by unified hypergraph: combining social media information and music content. In Proceedings of the 18th ACM international conference on Multimedia, pages 391–400, 2010.
  14. Sparse SYK and traversable wormholes. Journal of High Energy Physics, 2021(11):1–32, 2021.
  15. Spectral methods for data science: A statistical perspective. Foundations and Trends® in Machine Learning, 14(5):566–806, 2021.
  16. Community detection in hypergraphs: Optimal statistical limit and efficient algorithms. In International Conference on Artificial Intelligence and Statistics, pages 871–879, 2018.
  17. On the minimax misclassification ratio of hypergraph community detection. IEEE Transactions on Information Theory, 65(12):8095–8118, 2019.
  18. Optimal reconstruction of general sparse stochastic block models. arXiv preprint arXiv:2111.00697, 2021.
  19. Stochastic block model and community detection in sparse graphs: A spectral algorithm with optimal rate of recovery. In Conference on Learning Theory, pages 391–423, 2015.
  20. Amin Coja-Oghlan. Graph partitioning via adaptive spectral techniques. Combinatorics, Probability and Computing, 19(2):227–284, 2010.
  21. Exact recovery in the hypergraph stochastic block model: A spectral algorithm. Linear Algebra and its Applications, 593:45–73, 2020.
  22. Size biased couplings and the spectral gap for random regular graphs. The Annals of Probability, 46(1):72–125, 2018.
  23. Joshua Cooper. Adjacency spectra of random and complete hypergraphs. Linear Algebra and its Applications, 596:184–202, 2020.
  24. Strong consistency of spectral clustering for the sparse degree-corrected hypergraph stochastic block model. IEEE Transactions on Information Theory, 70(3):1962–1977, 2024.
  25. Optimal and exact recovery on general non-uniform hypergraph stochastic block model. arXiv preprint arXiv:2304.13139, 2023.
  26. Spectra of random regular hypergraphs. Electronic Journal of Combinatorics, 28(3):P3.36, 2021.
  27. Achieving the bayes error rate in synchronization and block models by SDP, robustly. IEEE Transactions on Information Theory, 66(6):3929–3953, 2020.
  28. Spectral techniques applied to sparse random graphs. Random Structures & Algorithms, 27(2):251–275, 2005.
  29. On the second eigenvalue of hypergraphs. Combinatorica, 15(1):43–65, 1995.
  30. Community detection in the hypergraph sbm: Optimal recovery given the similarity matrix. In Annual Conference Computational Learning Theory, 2023.
  31. Consistency of spectral partitioning of uniform hypergraphs under planted partition model. In Advances in Neural Information Processing Systems, pages 397–405, 2014.
  32. Consistency of spectral hypergraph partitioning under planted partition model. The Annals of Statistics, 45(1):289–315, 2017.
  33. Uniform hypergraph partitioning: Provable tensor methods and sampling techniques. The Journal of Machine Learning Research, 18(1):1638–1678, 2017.
  34. Venu Madhav Govindu. A tensor decomposition for geometric grouping and segmentation. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), volume 1, pages 1150–1157. IEEE, 2005.
  35. Community detection in the hypergraph stochastic block model and reconstruction on hypertrees. arXiv preprint arXiv:2402.06856, 2024.
  36. Weak recovery threshold for the hypergraph stochastic block model. In The Thirty Sixth Annual Conference on Learning Theory, pages 885–920. PMLR, 2023.
  37. Community detection in sparse networks via Grothendieck’s inequality. Probability Theory and Related Fields, 165(3-4):1025–1049, 2016.
  38. Deterministic tensor completion with hypergraph expanders. SIAM Journal on Mathematics of Data Science, 3(4):1117–1140, 2021.
  39. Stochastic blockmodels: First steps. Social networks, 5(2):109–137, 1983.
  40. Provable tensor factorization with missing data. In Advances in Neural Information Processing Systems, pages 1431–1439, 2014.
  41. Sharp impossibility results for hyper-graph testing. Advances in Neural Information Processing Systems, 34, 2021.
  42. Community detection for hypergraph networks via regularized tensor power iteration. arXiv preprint arXiv:1909.06503, 2019.
  43. Stochastic block model for hypergraphs: Statistical limits and a semidefinite programming approach. arXiv preprint arXiv:1807.02884, 2018.
  44. Estimating the number of communities by spectral methods. Electronic Journal of Statistics, 16(1):3315 – 3342, 2022.
  45. Concentration and regularization of random graphs. Random Structures & Algorithms, 51(3):538–561, 2017.
  46. Robust hypergraph clustering via convex relaxation of truncated mle. IEEE Journal on Selected Areas in Information Theory, 1(3):613–631, 2020.
  47. Consistent community detection in multi-layer network data. Biometrika, 107(1):61–73, 2020.
  48. Consistency of spectral clustering in stochastic block models. The Annals of Statistics, 43(1):215–237, 2015.
  49. News recommendation via hypergraph learning: encapsulation of user behavior and news content. In Proceedings of the sixth ACM international conference on Web search and data mining, pages 305–314, 2013.
  50. On the fundamental statistical limit of community detection in random hypergraphs. In Information Theory (ISIT), 2017 IEEE International Symposium on, pages 2178–2182. IEEE, 2017.
  51. A hypergraph model for representing scientific output. Scientometrics, 117(3):1361–1379, 2018.
  52. Laurent Massoulié. Community detection thresholds and the weak Ramanujan property. In Proceedings of the forty-sixth annual ACM symposium on Theory of computing, pages 694–703. ACM, 2014.
  53. Alignment and integration of complex networks by hypergraph-based spectral clustering. Physical Review E, 86(5):056111, 2012.
  54. Semidefinite programs on sparse random graphs and their application to community detection. In Proceedings of the forty-eighth annual ACM symposium on Theory of Computing, pages 814–827, 2016.
  55. Reconstruction and estimation in the planted partition model. Probability Theory and Related Fields, 162(3-4):431–461, 2015.
  56. Belief propagation, robust reconstruction and optimal recovery of block models. The Annals of Applied Probability, 26(4):2211–2256, 2016.
  57. Consistency thresholds for the planted bisection model. Electron. J. Probab, 21(21):1–24, 2016.
  58. A proof of the block model threshold conjecture. Combinatorica, 38(3):665–708, 2018.
  59. Random graph models of social networks. Proceedings of the national academy of sciences, 99(suppl 1):2566–2572, 2002.
  60. On spectral clustering: Analysis and an algorithm. In Advances in neural information processing systems, pages 849–856, 2002.
  61. Tensor sparsification via a bound on the spectral norm of random tensors. Information and Inference: A Journal of the IMA, 4(3):195–229, 2015.
  62. Community detection in the sparse hypergraph stochastic block model. Random Structures & Algorithms, 59(3):407–463, 2021.
  63. Spectral clustering of graphs with the bethe hessian. Advances in Neural Information Processing Systems, 27, 2014.
  64. Subhabrata Sen. Optimization on sparse random hypergraphs and spin glasses. Random Structures & Algorithms, 53(3):504–536, 2018.
  65. Normalized cuts and image segmentation. IEEE Transactions on pattern analysis and machine intelligence, 22(8):888–905, 2000.
  66. Spectral sparsification of hypergraphs. In Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, pages 2570–2581. SIAM, 2019.
  67. Sparse random hypergraphs: Non-backtracking spectra and community detection. Information and Inference: A Journal of the IMA, 13(1):iaae004, 2024.
  68. A hypergraph-based learning algorithm for classifying gene expression and arrayCGH data with prior knowledge. Bioinformatics, 25(21):2831–2838, 2009.
  69. Roman Vershynin. High-Dimensional Probability: An Introduction with Applications in Data Science. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, 2018.
  70. Van Vu. A simple svd algorithm for finding hidden partitions. Combinatorics, Probability and Computing, 27(1):124–140, 2018.
  71. Haixiao Wang. Fundamental limits and strong consistency of binary non-uniform hypergraph stochastic block models. 2023.
  72. Projected tensor power method for hypergraph community recovery. In International Conference on Machine Learning, pages 36285–36307. PMLR, 2023.
  73. Learning non-uniform hypergraph for multi-object tracking. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 8981–8988, 2019.
  74. Testing community structure for hypergraphs. The Annals of Statistics, 50(1):147–169, 2022.
  75. Community detection in censored hypergraph. arXiv preprint arXiv:2111.03179, 2021.
  76. Minimax rates of community detection in stochastic block models. The Annals of Statistics, 44(5):2252–2280, 2016.
  77. Qiaosheng Zhang and Vincent Y. F. Tan. Exact recovery in the general hypergraph stochastic block model. IEEE Transactions on Information Theory, 69(1):453–471, 2023.
  78. Community detection in general hypergraph via graph embedding. Journal of the American Statistical Association, pages 1–10, 2022.
  79. Learning with hypergraphs: Clustering, classification, and embedding. In Advances in neural information processing systems, pages 1601–1608, 2007.
  80. Sparse random tensors: Concentration, regularization and applications. Electronic Journal of Statistics, 15(1):2483–2516, 2021.
Citations (10)
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