Neural network predicts future wireless signals from noisy data
JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels
Information TheoryMachine Learning
Summary
Wireless signals change over time, and knowing their future state helps devices communicate better. The authors created a method called JEPA-kMMVAE that uses neural networks to predict future wireless channel information by learning from past noisy observations. Their approach organizes hidden patterns over time to improve predictions, especially when the input data is moderately or highly clear. However, when the data is very noisy, existing sequence-based methods can still do better.
What this means in practice
- •For wireless network engineers: Enhance channel state prediction to optimize communication in multi-antenna wireless systems when recent channel measurements are moderately clear.
- •For signal processing teams: Improve future signal estimation in time-varying environments by applying structured latent learning to reduce noise impact in predictive models.
Authors
Efstathios Chatziloizos, Konstantinos Vandikas, Aneta Vulgarakis Feljan, Zheng Chen, Nikolaos Pappas
Abstract
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.