Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework
This addresses privacy and efficiency issues in wireless communication systems, though it is incremental as it builds on existing deep learning methods.
The paper tackles the high communication overhead and privacy risks in centralized CSI feedback training by proposing Dig-CSI, a distributed framework where user equipment generate data locally instead of uploading it, achieving comparable performance with much lighter communication overhead.
The advent of deep learning (DL)-based models has significantly advanced Channel State Information (CSI) feedback mechanisms in wireless communication systems. However, traditional approaches often suffer from high communication overhead and potential privacy risks due to the centralized nature of CSI data processing. To address these challenges, we design a CSI feedback training framework called Dig-CSI, in which the dataset for training the CSI feedback model is produced by the distributed generators uploaded by each user equipment (UE), but not through local data upload. Each UE trains an autoencoder, where the decoder is considered as the distributed generator, with local data to gain reconstruction accuracy and the ability to generate. Experimental results show that Dig-CSI can train a global CSI feedback model with comparable performance to the model trained with classical centralized learning with a much lighter communication overhead.