Generative Model-Aided Continual Learning for CSI Feedback in FDD mMIMO-OFDM Systems
By: Guijun Liu , Yuwen Cao , Tomoaki Ohtsuki and more
Potential Business Impact:
Lets wireless signals work better everywhere.
Deep autoencoder (DAE) frameworks have demonstrated their effectiveness in reducing channel state information (CSI) feedback overhead in massive multiple-input multiple-output (mMIMO) orthogonal frequency division multiplexing (OFDM) systems. However, existing CSI feedback models struggle to adapt to dynamic environments caused by user mobility, requiring retraining when encountering new CSI distributions. Moreover, returning to previously encountered environments often leads to performance degradation due to catastrophic forgetting. Continual learning involves enabling models to incorporate new information while maintaining performance on previously learned tasks. To address these challenges, we propose a generative adversarial network (GAN)-based learning approach for CSI feedback. By using a GAN generator as a memory unit, our method preserves knowledge from past environments and ensures consistently high performance across diverse scenarios without forgetting. Simulation results show that the proposed approach enhances the generalization capability of the DAE framework while maintaining low memory overhead. Furthermore, it can be seamlessly integrated with other advanced CSI feedback models, highlighting its robustness and adaptability.
Similar Papers
Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems
Signal Processing
Lets phones share wireless info without spying.
Generative Decoding of Compressed CSI for MIMO Precoding Design
Signal Processing
Makes wireless signals faster and use less power.
CSI Prediction Frameworks for Enhanced 5G Link Adaptation: Performance-Complexity Trade-offs
Information Theory
Predicts wireless signals for faster internet.