Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels

Tomer Raviv, Sangwoo Park, Nir Shlezinger, Osvaldo Simeone, Yonina C. Eldar, Joonhyuk Kang

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

Abstract

Deep neural networks (DNNs) based digital receivers can potentially operate in complex environments. How-ever, the dynamic nature of communication channels implies that in some scenarios, DNN-based receivers should be periodically retrained in order to track temporal variations in the channel conditions. To this aim, frequent transmissions of lengthy pilot sequences are generally required, at the cost of substantial overhead. In this work we propose a DNN-aided symbol detector, Meta-ViterbiNet, that tracks channel variations with reduced overhead by integrating three complementary techniques: 1) We leverage domain knowledge to implement a model-based/data-driven equalizer, ViterbiNet, that operates with a relatively small number of trainable parameters; 2) We tailor a meta-learning procedure to the symbol detection problem, optimizing the hyperparameters of the learning algorithm to facilitate rapid online adaptation; and 3) We enable online training with short-length pilot blocks and coded data blocks. Numerical results demonstrate that Meta-ViterbiNet operates accurately in rapidly-varying channels, outperforming the previous best approach, based on ViterbiNet or conventional recurrent neural networks without meta-learning, by a margin of up to 0.6dB in bit error rate in various challenging scenarios. Index terms - Viterbi algorithm, meta-learning.

Original languageEnglish (US)
Title of host publication2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728194417
DOIs
StatePublished - Jun 2021
Externally publishedYes
Event2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021 - Virtual, Online
Duration: Jun 14 2021Jun 23 2021

Publication series

Name2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021 - Proceedings

Conference

Conference2021 IEEE International Conference on Communications Workshops, ICC Workshops 2021
CityVirtual, Online
Period6/14/216/23/21

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels'. Together they form a unique fingerprint.

Cite this