Contrastive Self-Supervised Learning for Wireless Power Control

TL;DR

This paper introduces a contrastive self-supervised learning method for wireless power control, pre-training a neural network backbone to improve performance and sample efficiency over traditional supervised approaches.

Contribution

It presents a novel contrastive learning framework for power control in wireless networks, combining self-supervised pre-training with limited labeled data fine-tuning.

Findings

Significant improvements in sum-throughput.

Enhanced sample efficiency.

Outperforms pure supervised learning methods.

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.