Distributionally robust learning based on dirichlet process prior in edge networks

Zhao Feng Zhang, Yue Chen, Jun Shan Zhang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

In order to meet the real-time performance requirements, intelligent decisions in Internet of things applications must take place right here right now at the network edge. Pushing the artificial intelligence frontier to achieve edge intelligence is nontrivial due to the constrained computing resources and limited training data at the network edge. To tackle these challenges, we develop a distributionally robust optimization (DRO)-based edge learning algorithm, where the uncertainty model is constructed to foster the synergy of cloud knowledge and local training. Specifically, the cloud transferred knowledge is in the form of a Dirichlet process prior distribution for the edge model parameters, and the edge device further constructs an uncertainty set centered around the empirical distribution of its local samples. The edge learning DRO problem, subject to these two distributional uncertainty constraints, is recast as a single-layer optimization problem using a duality approach. We then use an Expectation-Maximization algorithm-inspired method to derive a convex relaxation, based on which we devise algorithms to learn the edge model. Furthermore, we illustrate that the meta-learning fast adaptation procedure is equivalent to our proposed Dirichlet process prior-based approach. Finally, extensive experiments are implemented to showcase the performance gain over standard approaches using edge data only.

Original languageEnglish (US)
Pages (from-to)26-39
Number of pages14
JournalJournal of Communications and Information Networks
Volume5
Issue number1
StatePublished - Mar 2020
Externally publishedYes

Keywords

  • Dirichlet process
  • Distributionally robust optimization
  • Edge learning
  • Wasserstein distance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Distributionally robust learning based on dirichlet process prior in edge networks'. Together they form a unique fingerprint.

Cite this