Statistical Analysis of Multi-Relational Network Recovery

Zhi Wang, Xueying Tang, Jingchen Liu

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we develop asymptotic theories for a class of latent variable models for large-scale multi-relational networks. In particular, we establish consistency results and asymptotic error bounds for the (penalized) maximum likelihood estimators when the size of the network tends to infinity. The basic technique is to develop a non-asymptotic error bound for the maximum likelihood estimators through large deviations analysis of random fields. We also show that these estimators are nearly optimal in terms of minimax risk.

Original languageEnglish (US)
Article number540225
JournalFrontiers in Applied Mathematics and Statistics
Volume6
DOIs
StatePublished - Oct 19 2020
Externally publishedYes

Keywords

  • asymptotic analysis
  • knowledge graph completion
  • maximum likelihood estimation
  • multi-relational network
  • non-asymptotic analysis
  • risk
  • tail probability

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'Statistical Analysis of Multi-Relational Network Recovery'. Together they form a unique fingerprint.

Cite this