TY - JOUR
T1 - Information Bottleneck-Inspired Type Based Multiple Access for Remote Estimation in IoT Systems
AU - Zhu, Meiyi
AU - Feng, Chunyan
AU - Guo, Caili
AU - Jiang, Nan
AU - Simeone, Osvaldo
N1 - Funding Information:
The work of Osvaldo Simeone was supported in part by the European Research Council (ERC) through the European Union's Horizon 2020 Research and Innovation Programme under Grant 725731, in part by an Open Fellowship of the EPSRC under Grant EP/W024101/1, and in part by the European Union through Project CENTRIC under Grant 101096379. This work was supported in part by the Fundamental Research Funds for the Central Universities under Grant 2021XD-A01-1, and in part by the National Natural Science Foundation of China under Grant 92067202.
Publisher Copyright:
© 1994-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - Type-basedmultiple access (TBMA) is a semantics-aware multiple access protocol for remote inference. In TBMA, codewords are reused across transmitting sensors, with each codeword being assigned to a different observation value. Existing TBMA protocols are based on fixed shared codebooks and on conventional maximum-likelihood or Bayesian decoders, which require knowledge of the distributions of observations and channels. In this letter, we propose a novel design principle for TBMA based on the information bottleneck (IB). In the proposed IB-TBMA protocol, the shared codebook is jointly optimized with a decoder based on artificial neural networks (ANNs), so as to adapt to source, observations, and channel statistics based on data only. We also introduce the Compressed IB-TBMA (CIB-TBMA) protocol, which improves IB-TBMA by enabling a reduction in the number of codewords via an IB-inspired clustering phase. Numerical results demonstrate the importance of a joint design of codebook and neural decoder, and validate the benefits of codebook compression.
AB - Type-basedmultiple access (TBMA) is a semantics-aware multiple access protocol for remote inference. In TBMA, codewords are reused across transmitting sensors, with each codeword being assigned to a different observation value. Existing TBMA protocols are based on fixed shared codebooks and on conventional maximum-likelihood or Bayesian decoders, which require knowledge of the distributions of observations and channels. In this letter, we propose a novel design principle for TBMA based on the information bottleneck (IB). In the proposed IB-TBMA protocol, the shared codebook is jointly optimized with a decoder based on artificial neural networks (ANNs), so as to adapt to source, observations, and channel statistics based on data only. We also introduce the Compressed IB-TBMA (CIB-TBMA) protocol, which improves IB-TBMA by enabling a reduction in the number of codewords via an IB-inspired clustering phase. Numerical results demonstrate the importance of a joint design of codebook and neural decoder, and validate the benefits of codebook compression.
KW - Type-based multiple access
KW - information bottleneck
KW - machine learning
KW - semantic communi cation
UR - http://www.scopus.com/inward/record.url?scp=85153386158&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153386158&partnerID=8YFLogxK
U2 - 10.1109/LSP.2023.3266115
DO - 10.1109/LSP.2023.3266115
M3 - Article
AN - SCOPUS:85153386158
SN - 1070-9908
VL - 30
SP - 403
EP - 407
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
ER -