Power Allocation for Device-to-Device Interference Channel Using Truncated Graph Transformers

TL;DR

This paper introduces a novel graph transformer-based deep learning architecture for power allocation in device-to-device interference channels, outperforming existing methods and addressing heterophilous power distribution challenges.

Contribution

The paper proposes a new graph transformer model that improves power control in interference channels, overcoming limitations of traditional graph neural networks.

Findings

Achieves state-of-the-art performance across various network configurations.

Addresses heterophilous power distribution in interference channels.

Highlights a trade-off between model complexity and generality.

Abstract

Power control for the device-to-device interference channel with single-antenna transceivers has been widely analyzed with both model-based methods and learning-based approaches. Although the learning-based approaches, i.e., datadriven and model-driven, offer performance improvement, the widely adopted graph neural network suffers from learning the heterophilous power distribution of the interference channel. In this paper, we propose a deep learning architecture in the family of graph transformers to circumvent the issue. Experiment results show that the proposed methods achieve the state-of-theart performance across a wide range of untrained network configurations. Furthermore, we show there is a trade-off between model complexity and generality.