WiFo-E: A Scalable Wireless Foundation Model for End-to-End FDD Precoding in Communication Networks

TL;DR

WiFo-E is a scalable wireless foundation model using a Mixture-of-Experts Transformer architecture that improves end-to-end precoding in massive MIMO FDD systems, demonstrating strong generalization across configurations.

Contribution

Introduces WiFo-E, a novel scalable foundation model with multi-task pretraining and MoE architecture for end-to-end wireless precoding, addressing generalization and efficiency issues.

Findings

Outperforms traditional training methods in simulations

Shows strong generalization to unseen system configurations

Enhances training efficiency with sparse MoE architecture

Abstract

Accurate precoding in massive multiple-input multiple-output (MIMO) frequency-division duplexing (FDD) systems relies on efficient channel state information (CSI) acquisition. End-to-end learning frameworks improve performance by jointly optimizing this process, but they lack scalability and fail to generalize across different system configurations, such as varying numbers of antennas and users. To overcome this limitation, we introduce WiFo-E, a wireless foundation model designed for scalable end-to-end precoding. WiFo-E employs multi-task pretraining on a diverse set of configurations to learn transferable representations of underlying wireless principles. Central to the model is a sparse Mixture-of-Experts (MoE) Transformer architecture, which mitigates task interference and enhances training efficiency by activating specialized parameter subsets adaptively. Extensive simulations demonstrate that WiFo-E outperforms conventional per-configuration training and shows strong generalization to unseen system configurations, providing a flexible and efficient foundation for adaptive massive MIMO precoding.