Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems

• URL: http://arxiv.org/abs/2509.10490v1
• Date: Sun, 31 Aug 2025 07:46:16 GMT
• Title: Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems
• Authors: Yuwen Cao, Guijun Liu, Tomoaki Ohtsuki, Howard H. Yang, Tony Q. S. Quek,
• Abstract summary: We propose a novel gossiping generative adversarial network (Gossip-GAN)-aided CSI feedback training framework.<n>Gossip-GAN enables the CSI feedback training with low-overhead while preserving users' privacy.
• Score: 65.23921727688749
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The deep autoencoder (DAE) framework has turned out to be efficient in reducing the channel state information (CSI) feedback overhead in massive multiple-input multipleoutput (mMIMO) systems. However, these DAE approaches presented in prior works rely heavily on large-scale data collected through the base station (BS) for model training, thus rendering excessive bandwidth usage and data privacy issues, particularly for mMIMO systems. When considering users' mobility and encountering new channel environments, the existing CSI feedback models may often need to be retrained. Returning back to previous environments, however, will make these models perform poorly and face the risk of catastrophic forgetting. To solve the above challenging problems, we propose a novel gossiping generative adversarial network (Gossip-GAN)-aided CSI feedback training framework. Notably, Gossip-GAN enables the CSI feedback training with low-overhead while preserving users' privacy. Specially, each user collects a small amount of data to train a GAN model. Meanwhile, a fully distributed gossip-learning strategy is exploited to avoid model overfitting, and to accelerate the model training as well. Simulation results demonstrate that Gossip-GAN can i) achieve a similar CSI feedback accuracy as centralized training with real-world datasets, ii) address catastrophic forgetting challenges in mobile scenarios, and iii) greatly reduce the uplink bandwidth usage. Besides, our results show that the proposed approach possesses an inherent robustness.

Related papers

• Generative Model-Aided Continual Learning for CSI Feedback in FDD mMIMO-OFDM Systems [44.15961826013248]
  We propose a generative adversarial network (GAN)-based learning approach for CSI feedback.<n>By using a GAN generator as a memory unit, our method preserves knowledge from past environments and ensures consistently high performance.
  arXiv  Detail & Related papers  (2025-11-23T10:25:23Z)
• Generative MIMO Beam Map Construction for Location Recovery and Beam Tracking [67.65578956523403]
  This paper proposes a generative framework to recover location labels directly from sparse channel state information (CSI) measurements.<n>Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI.<n> Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios.
  arXiv  Detail & Related papers  (2025-11-21T07:25:49Z)
• CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing [15.607497819907227]
  We propose a unified framework named CSI-BERT2 for CSI prediction and classification tasks.<n>We introduce a two-stage training method that first uses a mask language model (MLM) to enable the model to learn general feature extraction from scarce datasets.<n>We also introduce an adaptive re-weighting layer (ARL) to enhance subcarrier representation and a multi-layer perceptron (MLP) based temporal embedding module.
  arXiv  Detail & Related papers  (2024-12-09T06:44:04Z)
• Finding the Missing Data: A BERT-inspired Approach Against Package Loss in Wireless Sensing [14.973433993744708]
  We propose a deep learning model based on Bidirectional Representations from Transformers (BERT) for CSI recovery. CSI-BERT can be trained in an self-supervised manner on the target dataset without the need for additional data. Experimental results demonstrate that CSI-BERT achieves lower error rates and faster speed compared to traditional methods.
  arXiv  Detail & Related papers  (2024-03-19T03:16:52Z)
• Dig-CSI: A Distributed and Generative Model Assisted CSI Feedback Training Framework [6.216538343278333]
  We design a CSI feedback training framework called Dig-CSI. 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. Experimental results show that Dig-CSI can train a global CSI feedback model with comparable performance to the model trained with classical centralized learning.
  arXiv  Detail & Related papers  (2023-12-10T15:55:57Z)
• A Low-Overhead Incorporation-Extrapolation based Few-Shot CSI Feedback Framework for Massive MIMO Systems [45.22132581755417]
  Accurate channel state information (CSI) is essential for downlink precoding in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems. However, obtaining CSI through feedback from the user equipment (UE) becomes challenging with the increasing scale of antennas and subcarriers. Deep learning-based methods have emerged for compressing CSI but these methods require substantial collected samples. Existing deep learning methods also suffer from dramatically growing feedback overhead owing to their focus on full-dimensional CSI feedback. We propose a low-overhead-Extrapolation based Few-Shot CSI
  arXiv  Detail & Related papers  (2023-12-07T06:01:47Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Adversarial training with informed data selection [53.19381941131439]
  Adrial training is the most efficient solution to defend the network against these malicious attacks. This work proposes a data selection strategy to be applied in the mini-batch training. The simulation results show that a good compromise can be obtained regarding robustness and standard accuracy.
  arXiv  Detail & Related papers  (2023-01-07T12:09:50Z)
• Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems [77.0986534024972]
  Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy.
  arXiv  Detail & Related papers  (2022-06-29T03:28:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.