Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation

TL;DR

This paper proposes InvCSINet, an invertible neural network framework for CSI feedback that preserves information during compression, effectively handles quantization and channel errors, and improves reconstruction accuracy in FDD massive MIMO systems.

Contribution

It introduces an invertible neural network-based CSI feedback method with integrated modules for quantization and error mitigation, ensuring information preservation and robustness.

Findings

Superior CSI recovery performance demonstrated in simulations

Enhanced robustness to practical impairments

Lightweight architecture with effective information preservation

Abstract

Deep learning has emerged as a promising solution for efficient channel state information (CSI) feedback in frequency division duplex (FDD) massive MIMO systems. Conventional deep learning-based methods typically rely on a deep autoencoder to compress the CSI, which leads to irreversible information loss and degrades reconstruction accuracy. This paper introduces InvCSINet, an information-preserving CSI feedback framework based on invertible neural networks (INNs). By leveraging the bijective nature of INNs, the model ensures information-preserving compression and reconstruction with shared model parameters. To address practical challenges such as quantization and channel-induced errors, we endogenously integrate an adaptive quantization module, a differentiable bit-channel distortion module and an information compensation module into the INN architecture. This design enables the network to learn and compensate the information loss during CSI compression, quantization, and noisy transmission, thereby preserving the CSI integrity throughout the feedback process. Simulation results validate the effectiveness of the proposed scheme, demonstrating superior CSI recovery performance and robustness to practical impairments with a lightweight architecture.