# Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networks

arXiv: https://arxiv.org/abs/2512.17466 · HTML: https://mlsanity.com/paper/2512.17466/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [Effects of padding on LSTMs and CNNs](https://mlsanity.com/paper/1903.07288/) (2019)
- [Foundations of User-Centric Cell-Free Massive MIMO](https://mlsanity.com/paper/2108.02541/) (2021)
- [Making Cell-Free Massive MIMO Competitive With MMSE Processing and Centralized Implementation](https://mlsanity.com/paper/1903.10611/) (2019)
- [Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training](https://mlsanity.com/paper/1907.13257/) (2019)
- [User-centric Cell-free Massive MIMO Networks: A Survey of Opportunities, Challenges and Solutions](https://mlsanity.com/paper/2104.14589/) (2021)
- [Padding Module: Learning the Padding in Deep Neural Networks](https://mlsanity.com/paper/2301.04608/) (2023)
- [Closed-form max-min power control for some cellular and cell-free massive MIMO networks](https://mlsanity.com/paper/2205.00429/) (2022)
- [Downlink Resource Allocation in Multiuser Cell-free MIMO Networks with User-centric Clustering](https://mlsanity.com/paper/2108.06316/) (2021)
- [Accelerated Projected Gradient Method for the Optimization of Cell-Free Massive MIMO Downlink](https://mlsanity.com/paper/2201.04440/) (2022)
- [Ultra-Dense Cell-Free Massive MIMO for 6G: Technical Overview and Open Questions](https://mlsanity.com/paper/2401.03898/) (2024)
- [Transformer-Based Power Optimization for Max-Min Fairness in Cell-Free Massive MIMO](https://mlsanity.com/paper/2503.03561/) (2025)
- [Learning Image Labels On-the-fly for Training Robust Classification Models](https://mlsanity.com/paper/2009.10325/) (2020)
- [A Deep Learning Approach for User-Centric Clustering in Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/2410.02775/) (2024)
- [A New Look at Cell-Free Massive MIMO: Making It Practical With Dynamic Cooperation](https://mlsanity.com/paper/1906.10853/) (2019)
- [Centralized and Distributed Power Allocation for Max-Min Fairness in Cell-Free Massive MIMO](https://mlsanity.com/paper/2112.15490/) (2021)
- [Joint AP-UE Association and Precoding for SIM-Aided Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/2409.12870/) (2024)

## Built on by (most cited first, 1 of 1)

- [Tree Meets Transformer: A Hybrid Architecture for Scalable Power Allocation in Cell-Free Networks](https://mlsanity.com/paper/2512.22639/) (2025)

## Abstract (arXiv)

Optimal AP clustering and power allocation are critical in user-centric cell-free massive MIMO systems. Existing deep learning models lack flexibility to handle dynamic network configurations. Furthermore, many approaches overlook pilot contamination and suffer from high computational complexity. In this paper, we propose a lightweight transformer model that overcomes these limitations by jointly predicting AP clusters and powers solely from spatial coordinates of user devices and AP. Our model is architecture-agnostic to users load, handles both clustering and power allocation without channel estimation overhead, and eliminates pilot contamination by assigning users to AP within a pilot reuse constraint. We also incorporate a customized linear attention mechanism to capture user-AP interactions efficiently and enable linear scalability with respect to the number of users. Numerical results confirm the model's effectiveness in maximizing the minimum spectral efficiency and providing near-optimal performance while ensuring adaptability and scalability in dynamic scenarios.