Exact Recovery in Community Detection With Continuous-Valued Side Information

The community detection problem, as a special case of inference on graphs, has received much attention lately. However, in the presence of continuous-valued side information, the behavior of a sharp threshold for exact recovery has remained open, and is addressed in this letter. The new proof presented herein has the further advantage of closing the gap between necessary and sufficient conditions for exact recovery threshold that has existed in community detection under finite-alphabet side information.

[1]  Aria Nosratinia,et al.  Side Information in Recovering a Single Community: Information Theoretic Limits , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[2]  Emmanuel Abbe,et al.  Proof of the Achievability Conjectures for the General Stochastic Block Model , 2018 .

[3]  R. Paley,et al.  A note on analytic functions in the unit circle , 1932, Mathematical Proceedings of the Cambridge Philosophical Society.

[4]  Emmanuel Abbe,et al.  Exact Recovery in the Stochastic Block Model , 2014, IEEE Transactions on Information Theory.

[5]  Cristopher Moore,et al.  Phase transition in the detection of modules in sparse networks , 2011, Physical review letters.

[6]  Alexandre Proutière,et al.  Community Detection via Random and Adaptive Sampling , 2014, COLT.

[7]  Aria Nosratinia,et al.  Community Detection With Side Information: Exact Recovery Under the Stochastic Block Model , 2018, IEEE Journal of Selected Topics in Signal Processing.

[8]  Elchanan Mossel,et al.  Reconstruction and estimation in the planted partition model , 2012, Probability Theory and Related Fields.

[9]  Laurent Massoulié,et al.  Community detection thresholds and the weak Ramanujan property , 2013, STOC.

[10]  Elchanan Mossel,et al.  Consistency thresholds for the planted bisection model , 2016 .

[11]  Aria Nosratinia,et al.  EXIT analysis for belief propagation in degree-correlated stochastic block models , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[12]  Aria Nosratinia,et al.  Belief Propagation with Side Information for Recovering a Single Community , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[13]  Emmanuel Abbe,et al.  Community Detection in General Stochastic Block models: Fundamental Limits and Efficient Algorithms for Recovery , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[14]  Aria Nosratinia,et al.  Exact recovery in the binary stochastic block model with binary side information , 2017, 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[15]  Elchanan Mossel,et al.  Density Evolution in the Degree-correlated Stochastic Block Model , 2015, COLT.