A Spatially Separable Attention Mechanism for massive MIMO CSI Feedback

TL;DR

This paper introduces STNet, a lightweight transformer with a spatially separable attention mechanism for massive MIMO CSI feedback, significantly reducing computational complexity while outperforming state-of-the-art models in some scenarios.

Contribution

The paper proposes a novel spatially separable attention mechanism for transformers, enabling efficient CSI feedback in massive MIMO systems with reduced resource requirements.

Findings

STNet outperforms existing models in certain scenarios.

STNet uses approximately one-tenth of the resources of traditional transformers.

The spatially separable attention mechanism reduces computational complexity.

Abstract

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the feedback overhead several compressive sensing (CS) techniques were implemented in recent years but these techniques are often iterative and are computationally complex to realize in power-constrained user equipment (UE). Hence, a data-based deep learning approach took over in these recent years introducing a variety of neural networks for CSI compression. Specifically, transformer-based networks have been shown to achieve state-of-the-art performance. However, the multi-head attention operation, which is at the core of transformers, is computationally complex making transformers difficult to implement on a UE. In this work, we present a lightweight transformer named STNet which uses a spatially separable attention mechanism that is significantly less complex than the traditional full-attention. Equipped with this, STNet outperformed state-of-the-art models in some scenarios with approximately $1/10^{th}$ of the resources.