From learning to meta-learning: Reduced training overhead and complexity for communication systems

Osvaldo Simeone, Sangwoo Park, Joonhyuk Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed when the system configuration changes. The resulting inefficiency in terms of data and training time requirements can be mitigated, if domain knowledge is available, by selecting a suitable model class and learning procedure, collectively known as inductive bias. However, it is generally difficult to encode prior knowledge into an inductive bias, particularly with black-box model classes such as neural networks. Meta-learning provides a way to automatize the selection of an inductive bias. Meta-learning leverages data or active observations from tasks that are expected to be related to future, and a priori unknown, tasks of interest. With a meta-trained inductive bias, training of a machine learning model can be potentially carried out with reduced training data and/or time complexity. This paper provides a high-level introduction to meta-learning with applications to communication systems.

Original languageEnglish (US)
Title of host publication2nd 6G Wireless Summit 2020
Subtitle of host publicationGain Edge for the 6G Era, 6G SUMMIT 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728160474
DOIs
StatePublished - Mar 2020
Externally publishedYes
Event2nd 6G Wireless Summit, 6G SUMMIT 2020 - Levi, Lapland, Finland
Duration: Mar 17 2020Mar 20 2020

Publication series

Name2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020

Conference

Conference2nd 6G Wireless Summit, 6G SUMMIT 2020
CountryFinland
CityLevi, Lapland
Period3/17/203/20/20

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Hardware and Architecture
  • Signal Processing
  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications
  • Instrumentation

Fingerprint Dive into the research topics of 'From learning to meta-learning: Reduced training overhead and complexity for communication systems'. Together they form a unique fingerprint.

Cite this