Tree Meets Transformer: A Hybrid Architecture for Scalable Power Allocation in Cell-Free Networks

TL;DR

This paper introduces a hybrid Tree-Transformer model for scalable power allocation in large cell-free wireless networks, combining hierarchical feature compression with efficient Transformer processing to handle dynamic user loads effectively.

Contribution

The paper presents a novel Tree-Transformer architecture that reduces computational complexity to logarithmic depth, enabling scalable and efficient power allocation without retraining.

Findings

Achieves near-optimal power allocation performance.

Reduces inference time significantly compared to full-attention models.

Handles large, variable user sets efficiently.

Abstract

Power allocation remains a fundamental challenge in wireless communication networks, particularly under dynamic user loads and large-scale deployments. While Transformerbased models have demonstrated strong performance, their computational cost scales poorly with the number of users. In this work, we propose a novel hybrid Tree-Transformer architecture that achieves scalable per-user power allocation. Our model compresses user features via a binary tree into a global root representation, applies a Transformer encoder solely to this root, and decodes per-user uplink and downlink powers through a shared decoder. This design achieves logarithmic depth and linear total complexity, enabling efficient inference across large and variable user sets without retraining or architectural changes. We evaluate our model on the max-min fairness problem in cellfree massive MIMO systems and demonstrate that it achieves near-optimal performance while significantly reducing inference time compared to full-attention baselines.