Improved Clustering Algorithms for the Bipartite Stochastic Block Model

DOI10.1109/TIT.2021.3130683MaRDI QIDQ5080038zbMATH OpenFDO

Authors Suzanne Sigalla, Alexandre B. Tsybakov, Mohamed Ndaoud

Publication date 30 May 2022

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1911.07987

zbMATH Keywords

polynomial time algorithmsBipartite Stochastic Block Model (BSBM)

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50)

Abstract: We establish sufficient conditions of exact and almost full recovery of the node partition in Bipartite Stochastic Block Model (BSBM) using polynomial time algorithms. First, we improve upon the known conditions of almost full recovery by spectral clustering algorithms in BSBM. Next, we propose a new computationally simple and fast procedure achieving exact recovery under milder conditions than the state of the art. Namely, if the vertex sets $V_1$ and $V_2$ in BSBM have sizes $n_1$ and $n_2$, we show that the condition $p=Omegaleft(maxleft(sqrtfraclog{n}_1{n}_1{n}_2,fraclog{n}_1{n}_{2}ight)ight)$ on the edge intensity $p$ is sufficient for exact recovery witin $V_1$. This condition exhibits an elbow at $n_{2}asymp{n}_{1}log{n}_1$ between the low-dimensional and high-dimensional regimes. The suggested procedure is a variant of Lloyd's iterations initialized with a well-chosen spectral estimator leading to what we expect to be the optimal condition for exact recovery in BSBM. {The optimality conjecture is supported by showing that, for a supervised oracle procedure, such a condition is necessary to achieve exact recovery.} The key elements of the proof techniques are different from classical community detection tools on random graphs. Numerical studies confirm our theory, and show that the suggested algorithm is both very fast and achieves {almost the same} performance as the supervised oracle. Finally, using the connection between planted satisfiability problems and the BSBM, we improve upon the sufficient number of clauses to completely recover the planted assignment.

Cited in

(7)

• A fast permuation-based algorithm for block clustering
• Leave-one-out singular subspace perturbation analysis for spectral clustering
• Improved Approximation Algorithms for Bipartite Correlation Clustering
• scientific article; zbMATH DE number 7626708 (Why is no real title available?)
• Strong consistency guarantees for clustering high-dimensional bipartite graphs with the spectral method
• An \({\ell_p}\) theory of PCA and spectral clustering
• Sharp optimal recovery in the two component Gaussian mixture model

This page was built for publication: Improved Clustering Algorithms for the Bipartite Stochastic Block Model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5080038)