Coreset-based data reduction for machine learning at the edge

Hanlin Lu, Ting He, Shiqiang Wang

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter covers the issue of reducing the communication cost for machine learning at the edge from the perspective of data compression. Unlike traditional data compression schemes that aim at supporting the reconstruction of the original data, here the compression only needs to support the learning of the models that need to be learned from the original data, in order to support AI applications in a bandwidth-limited edge network. This lowered goal opens the door to a variety of application-specific lossy compression schemes designed to support machine learning. The focus in this chapter is on a subset of such schemes that can construct a weighted dataset much smaller than the original dataset that can function as a replacement of the original dataset in learning tasks, known as coreset. It reviews the history of coresets and their limitations, and then details two recently proposed improvements on (1) robust coreset construction and (2) integration of coreset construction and quantization.

Original languageEnglish (US)
Title of host publicationArtificial Intelligence for Edge Computing
PublisherSpringer International Publishing
Pages223-264
Number of pages42
ISBN (Electronic)9783031407871
ISBN (Print)9783031407864
DOIs
StatePublished - Dec 21 2023

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Engineering

Fingerprint

Dive into the research topics of 'Coreset-based data reduction for machine learning at the edge'. Together they form a unique fingerprint.

Cite this