Generative Model-Aided Continual Learning for CSI Feedback in FDD mMIMO-OFDM Systems

2025-11-23

AI Summary

In FDD massive MIMO-OFDM systems, user mobility induces time-varying channel state information (CSI) distributions, posing dual challenges of poor dynamic adaptability and catastrophic forgetting for existing CSI feedback models. To address this, we propose a generative-model-driven continual learning framework: a generative adversarial network (GAN) generator serves as an implicit memory unit, preserving historical channel feature knowledge without explicit replay or retraining—achieving low storage overhead. Coupled with a deep autoencoder (DAE), the framework enables end-to-end CSI compression and reconstruction. Experimental results demonstrate significantly enhanced generalization and robustness across diverse and rapidly switching propagation scenarios, while maintaining low feedback overhead. Moreover, the method is fully compatible with state-of-the-art CSI feedback architectures. This work establishes a novel paradigm for efficient, continual channel sensing in dynamic wireless environments.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

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.

Problem

• Reducing CSI feedback overhead in massive MIMO-OFDM systems
• Adapting to dynamic environments caused by user mobility
• Preventing catastrophic forgetting when encountering new CSI distributions

Innovation

• GAN generator serves as memory unit for knowledge retention
• Enables continual learning without catastrophic forgetting in CSI feedback
• Seamlessly integrates with existing CSI feedback models