Contextual Stochastic Block Models
Name
8077-contextual-stochastic-block-models.pdf
Description
Published version
Size
336.16 KB
Format
Adobe PDF
Checksum (MD5)
71ac6992a460db0ab2eba0af9826e088
Author(s)
Deshpande, Yash
Montanari, Andrea
Mossel, Elchanan
Sen, Subhabrata
Date Issued
2018
Citation
Deshpande, Yash, Montanari, Andrea, Mossel, Elchanan and Sen, Subhabrata. 2018. "Contextual Stochastic Block Models."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. We provide the first information theoretic tight analysis for inference of latent community structure given a sparse graph along with high dimensional node covariates, correlated with the same latent communities. Our work bridges recent theoretical breakthroughs in the detection of latent community structure without nodes covariates and a large body of empirical work using diverse heuristics for combining node covariates with graphs for inference. The tightness of our analysis implies in particular, the information theoretical necessity of combining the different sources of information. Our analysis holds for networks of large degrees as well as for a Gaussian version of the model.
MIT Department
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/8077-contextual-stochastic-block-models
