Contrastive Self-Supervised Learning for Wireless Power Control
Abstract
We propose a new approach for power control in wireless networks using self-supervised learning. We partition a multi-layer perceptron that takes as input the channel matrix and outputs the power control decisions into a backbone and a head, and we show how we can use contrastive learning to pre-train the backbone so that it produces similar embeddings at its output for similar channel matrices and vice versa, where similarity is defined in an information-theoretic sense by identifying the interference links that can be optimally treated as noise. The backbone and the head are then fine-tuned using a limited number of labeled samples. Simulation results show the effectiveness of the proposed approach, demonstrating significant gains over pure supervised learning methods in both sum-throughput and sample efficiency.
Keywords
Cite
@article{arxiv.2010.11909,
title = {Contrastive Self-Supervised Learning for Wireless Power Control},
author = {Navid Naderializadeh},
journal= {arXiv preprint arXiv:2010.11909},
year = {2021}
}
Comments
Final version to be presented at IEEE ICASSP 2021. Code available at https://github.com/navid-naderi/ContrastiveSSL_WirelessPowerControl