CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing

2025-10-14

AI Summary

To address the challenges of poor robustness to non-Gaussian noise, weak cross-channel generalization, and high computational overhead in CSI prediction for massive MIMO systems, this paper proposes a lightweight hybrid architecture integrating convolutional residuals, ShuffleNet-style channel shuffling, adaptive correction, and Transformer modules. To enable fair and comprehensive evaluation, we introduce CSI-RRG—the first standardized benchmark dataset covering diverse scenarios with over 300,000 samples. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches on 88.9% and 43.8% of test cases under TDD and FDD configurations, respectively. Compared to the strongest baseline, LLM4CP, our model reduces computational cost by 3–5× while significantly improving prediction accuracy, robustness to noise, cross-channel generalization capability, and inference efficiency.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Channel state information (CSI) prediction is a promising strategy for ensuring reliable and efficient operation of massive multiple-input multiple-output (mMIMO) systems by providing timely downlink (DL) CSI. While deep learning-based methods have advanced beyond conventional model-driven and statistical approaches, they remain limited in robustness to practical non-Gaussian noise, generalization across diverse channel conditions, and computational efficiency. This paper introduces CSI-4CAST, a hybrid deep learning architecture that integrates 4 key components, i.e., Convolutional neural network residuals, Adaptive correction layers, ShuffleNet blocks, and Transformers, to efficiently capture both local and long-range dependencies in CSI prediction. To enable rigorous evaluation, this work further presents a comprehensive benchmark, CSI-RRG for Regular, Robustness and Generalization testing, which includes more than 300,000 samples across 3,060 realistic scenarios for both TDD and FDD systems. The dataset spans multiple channel models, a wide range of delay spreads and user velocities, and diverse noise types and intensity degrees. Experimental results show that CSI-4CAST achieves superior prediction accuracy with substantially lower computational cost, outperforming baselines in 88.9% of TDD scenarios and 43.8% of FDD scenario, the best performance among all evaluated models, while reducing FLOPs by 5x and 3x compared to LLM4CP, the strongest baseline. In addition, evaluation over CSI-RRG provides valuable insights into how different channel factors affect the performance and generalization capability of deep learning models. Both the dataset (https://huggingface.co/CSI-4CAST) and evaluation protocols (https://github.com/AI4OPT/CSI-4CAST) are publicly released to establish a standardized benchmark and to encourage further research on robust and efficient CSI prediction.

Problem

• Predicting channel state information for reliable mMIMO system operation
• Addressing robustness limitations under non-Gaussian noise conditions
• Improving generalization across diverse wireless channel scenarios

Innovation

• Hybrid deep learning integrates CNN residuals and Transformers
• Adaptive correction layers enhance robustness to noise
• ShuffleNet blocks reduce computational costs significantly