# A Spatially Separable Attention Mechanism for massive MIMO CSI Feedback

arXiv: https://arxiv.org/abs/2208.03369 · HTML: https://mlsanity.com/paper/2208.03369/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2022.

## Built on by (most cited first, 7 of 7)

- [Spectral Temporal Graph Neural Network for massive MIMO CSI Prediction](https://mlsanity.com/paper/2312.02159/) (2023)
- [Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention](https://mlsanity.com/paper/2509.19331/) (2025)
- [Graph Neural Networks-Based User Pairing in Wireless Communication Systems](https://mlsanity.com/paper/2306.00717/) (2023)
- [Auto-CsiNet: Scenario-customized Automatic Neural Network Architecture Generation for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2311.15950/) (2023)
- [Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework](https://mlsanity.com/paper/2312.05921/) (2023)
- [Universal Auto-encoder Framework for MIMO CSI Feedback](https://mlsanity.com/paper/2403.00299/) (2024)
- [CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing](https://mlsanity.com/paper/2510.12996/) (2025)

## Abstract (arXiv)

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 1/10th of the resources.