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

TL;DR

ChannelKAN is a hybrid CNN-KAN model that enhances multi-scale frequency domain information for accurate CSI prediction in high-mobility massive MIMO-OFDM systems.

Contribution

It introduces a novel hybrid CNN-KAN architecture with multi-scale frequency enhancement for joint local and long-range CSI sequence modeling.

Findings

Outperforms RNN, LSTM, GRU, CNN, and Transformer baselines in NMSE, SE, and BER.

Effectively captures local spatial-frequency correlations and long-range temporal dependencies.

Ablation studies validate the effectiveness of each module.

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.