Weighted message passing and minimum energy flow for heterogeneous stochastic block models with side information
Name
18-573.pdf
Description
Published version
Size
440.96 KB
Format
Adobe PDF
Checksum (MD5)
e9319e05e39546f5e3fd3411cfaef15e
Author(s)
Tony Cai, T
Liang, T
Rakhlin, A
Date Issued
January 1, 2020
Journal
Journal of Machine Learning Research
Citation
Tony Cai, T, Liang, T and Rakhlin, A. 2020. "Weighted message passing and minimum energy flow for heterogeneous stochastic block models with side information." Journal of Machine Learning Research, 21.
Version
Final published version
Abstract
© 2020 T. Tony Cai, Tengyuan Liang and Alexander Rakhlin. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v21/18-573.html. We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighted message passing algorithm to reconstruct labels for SBM based on the minimum energy flow and the eigenvectors of a certain Markov transition matrix. The general SBM considered in this paper allows for unequal-size communities, degree heterogeneity, and different connection probabilities among blocks. We focus on how to optimally weigh the message passing to improve misclassification.
MIT Department
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://jmlr.org/papers/v21/18-573.html
