JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels

Key points

• The main challenge is to exploit temporal correlation while distinguishing channel evolution from observation noise.1
• 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.1
• The framework supports direct prediction and residual corrections relative to the latest latent state and noisy CSI observation.1
• 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.1

Sources (1)

• [1]JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 09:58 AM

  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.

Extractive summary: sentences quoted from the sources.