Contrastive Self-Supervised Learning for Wireless Power Control
This work addresses the problem of improving power control efficiency in wireless networks, offering a domain-specific incremental advancement.
The paper tackles power control in wireless networks by proposing a contrastive self-supervised learning method to pre-train a neural network backbone, which is then fine-tuned with limited labeled data, resulting in significant gains in sum-throughput and sample efficiency over pure supervised learning methods.
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.