Organizations: Ericsson Research, Stockholm, Sweden · Department of Computer and Information Science, Linköping University, Linköping, Sweden · Department of Electrical Engineering, Linköping University, Linköping, Sweden
This paper considers channel state information (CSI) prediction using neural networks for time-varying multi-antenna channels from noisy historical observations. The main challenge is to exploit temporal correlation while distinguishing channel evolution from observation noise. We propose JEPA-kMMVAE, which combines a joint-embedding predictive architecture with a k-memory Markov variational autoencoder to predict future CSI through temporally structured latent representations. The framework supports direct prediction and residual corrections relative to the latest latent state and noisy CSI observation. Simulation results show that the residual configuration outperforms the evaluated baselines at moderate and high input CSI signal-to-noise ratios, while sequence baselines remain more accurate under stronger noise.
Figures & tables
Figure 1: Causal CSI prediction from C noisy observations. The predictor maps the available history Yt to the next clean snapshot estimate xt+1 . The future target is available only for training and evaluation.
Figure 2: JEPA- k MMVAE residual prediction framework. Noisy history drives latent prediction and residual CSI decoding. The dashed branch supplies clean latent targets during training; the CSI output is supervised by the clean future snapshot.
Method
5 dB
10 dB
15 dB
20 dB
25 dB
Persistence
−4.75
−9.24
−12.94
−15.35
−16.50
Linear extrapolation
+2.01
−2.95
−7.84
−12.49
−16.53
Learned linear
−8.98±0.01
−11.32±0.01
−12.43±0.03
−12.85±0.03
−12.99±0.04
GRU
−9.69±0.01
−12.48±0.06
−14.28±0.13
−15.10±0.17
−15.41±0.19
LSTM
−9.34±0.03
−11.73±0.06
−13.14±0.14
−13.75±0.18
−13.97±0.20
Transformer
−10.02±0.06
−12.44±0.06
−13.72±0.07
−14.23±0.07
−14.41±0.07
Table 1: Prediction NMSE in dB (lower is better). Values for learned models are mean ± sample standard deviation over three runs. Both JEPA- k MMVAE variants use d=64 . Bold indicates the lowest mean in each column.
Figure 3: Direct and residual JEPA- k MMVAE prediction at d=64 . Curves show mean CSI prediction NMSE; error bars denote ± one sample standard deviation over three runs.
This paper considers neural channel state information (CSI) compression for time-varying massive multiple-input multiple-output (MIMO) channels in frequency division duplex (FDD) systems with limited feedback resources. The main challenge lies in obtaining a compact and efficient representation of the CSI given that it exhibits strong temporal correlation across successive snapshots. Existing memoryless compression models do not exploit this property, while simple temporal extensions often incorporate multiple observations without explicitly modeling the latent dynamics. We propose a context-aware compression framework based on a k-memory Markov variational autoencoder (k-MMVAE), which uses a finite temporal window to capture the evolution of CSI in the latent space. The model introduces Markov-structured latent dynamics with finite memory, enabling efficient use of temporal dependencies for compression. Simulation results show that the proposed approach improves target CSI reconstruction performance compared to memoryless and weakly sequential baselines, particularly at low and moderate compression rates. These results suggest that explicit latent temporal modeling can provide an effective mechanism for CSI compression under limited feedback constraints.
Ericsson Research, Stockholm, Sweden · Department of Computer and Information Science, Linköping University, Linköping, Sweden · Department of Electrical Engineering, Linköping University, Linköping, Sweden
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.
Nanqing Jiang, Zhangyao Song, Tao Guo +2
School of Cyber Science and Engineering, Southeast University, Nanjing, China
Reliable prediction of time-varying channel state information (CSI) is essential for efficient wireless communication. Each CSI frame is a matrix-valued representation of the wireless channel response, and a sequence of CSI frames forms a temporal channel trajectory. Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates. This limitation is particularly problematic in multi-step CSI prediction, where the target is a sequence of future CSI matrices, and downstream decisions such as beamforming or scheduling may fail if any part of the predicted trajectory is unreliable. We propose trajectory-adaptive calibration and error profiling with conformal risk control (TRACE-CRC), a method for trajectory-aware uncertainty quantification in multi-step CSI prediction. TRACE-CRC constructs Frobenius-norm uncertainty balls around predicted CSI matrices and controls the risk that at least one future frame is uncovered. Instead of calibrating each future step independently, TRACE-CRC combines future-step-dependent error profiling, trajectory difficulty stratification, and learn-then-test (LTT) risk control. Empirically, TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections, while avoiding the trajectory undercoverage of compact stepwise and adaptive conformal baselines.
Kiarash Rezaei, Mehdi Sattari, Javad Aliakbari +3
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden