Recovering communities in the general stochastic block model without knowing the parameters

Abstract

Most recent developments on the stochastic block model (SBM) rely on the knowledge of the model parameters, or at least on the number of communities. This paper introduces efficient algorithms that do not require such knowledge and yet achieve the optimal information-theoretic tradeoffs identified in [AS15] for linear size communities. The results are three-fold: (i) in the constant degree regime, an algorithm is developed that requires only a lower-bound on the relative sizes of the communities and detects communities with an optimal accuracy scaling for large degrees; (ii) in the regime where degrees are scaled by $\omega (1)$ (diverging degrees), this is enhanced into a fully agnostic algorithm that only takes the graph in question and simultaneously learns the model parameters (including the number of communities) and detects communities with accuracy $1-o(1)$, with an overall quasi-linear complexity; (iii) in the logarithmic degree regime, an agnostic algorithm is developed that learns the parameters and achieves the optimal CH-limit for exact recovery, in quasi-linear time. These provide the first algorithms affording efficiency, universality and information-theoretic optimality for strong and weak consistency in the general SBM with linear size communities.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1503.00609

References in corpus (8)

• Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
• Stochastic blockmodels with growing number of classes
• Stochastic Block Models and Reconstruction
• Community detection in general stochastic block models: fundamental limits and efficient recovery algorithms
• Accurate Community Detection in the Stochastic Block Model via Spectral Algorithms
• Achieving Optimal Misclassification Proportion in Stochastic Block Model
• Private Graphon Estimation for Sparse Graphs
• Community Detection in Networks using Graph Distance

Cited by in corpus (9)

• ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
• Iterative Collaborative Filtering for Sparse Matrix Estimation
• Reducing Crowdsourcing to Graphon Estimation, Statistically
• Amortized Probabilistic Detection of Communities in Graphs
• Clustering in Block Markov Chains
• Biclustering and Boolean Matrix Factorization in Data Streams
• Achieving the Bayes Error Rate in Synchronization and Block Models by SDP, Robustly
• A Random Dot Product Model for Weighted Networks
• Compressive Sensing for cut improvement and local clustering