ChannelKAN: Multi-Scale Dual-Domain Channel Prediction via Hybrid CNN-KAN Architecture

2026-05-11

AI Summary

This work addresses the challenge that existing deep learning methods struggle to simultaneously capture local time-frequency variations and long-range nonlinear dependencies in channel state information (CSI) sequences, which limits the performance of massive MIMO-OFDM systems under high-mobility conditions. To overcome this, we propose ChannelKAN, the first framework to integrate Kolmogorov–Arnold Networks (KANs) into wireless channel prediction. ChannelKAN combines KANs with CNNs in a hybrid architecture that enables multi-scale CSI modeling across both time and frequency domains. Through dual-domain expansion, multi-scale frequency enhancement, and an adaptive fusion mechanism, it effectively isolates critical spectral components while jointly capturing local correlations and global temporal dynamics. Evaluated on the QuaDRiGa dataset, ChannelKAN consistently outperforms RNN, LSTM, GRU, CNN, and Transformer baselines across diverse velocities and SNR levels, achieving lower NMSE, higher spectral efficiency, and reduced bit error rates.

Abstract

Accurate channel state information (CSI) prediction is essential for improving the reliability and spectral efficiency of massive MIMO-OFDM systems in high-mobility scenarios. Existing deep learning methods struggle to jointly capture short-term local variations and long-range nonlinear dependencies in CSI sequences. To address this challenge, we propose ChannelKAN, a hybrid CNN-KAN channel prediction model with multi-scale frequency domain information enhancement. The key insight is that CNNs and Kolmogorov-Arnold Networks (KANs) are naturally complementary: CNNs extract intra-time-step local spatial-frequency correlations, while KANs with learnable Chebyshev polynomial activations fit inter-time-step nonlinear temporal evolution in a holistic manner. Specifically, a dual-domain expansion module first generates complementary frequency-domain and delay-domain CSI representations. A multi-scale frequency information enhancement module then retains dominant spectral components at multiple scales to strengthen key features and suppress noise. Next, a CNN-KAN feature extraction module captures local correlations via cascaded convolutions and models long-range dependencies via Chebyshev KAN layers. Finally, a dual-domain fusion module adaptively integrates features from both branches to produce the prediction. Experiments on 3GPP-compliant QuaDRiGa datasets demonstrate that ChannelKAN outperforms RNN, LSTM, GRU, CNN, and Transformer baselines in normalized mean square error (NMSE), spectral efficiency (SE), and bit error rate (BER) across various velocities and signal-to-noise ratios. Ablation studies further confirm the effectiveness of each proposed module.

Problem

• channel state information
• massive MIMO-OFDM
• high-mobility
• CSI prediction
• nonlinear dependencies

Innovation

• ChannelKAN
• Kolmogorov-Arnold Networks
• multi-scale frequency enhancement
• dual-domain fusion
• CSI prediction