UVeQFed: Universal Vector Quantization for Federated Learning

@article{Shlezinger2021UVeQFedUV,
  title={UVeQFed: Universal Vector Quantization for Federated Learning},
  author={Nir Shlezinger and M. Chen and Yonina C. Eldar and H. V. Poor and Shuguang Cui},
  journal={IEEE Transactions on Signal Processing},
  year={2021},
  volume={69},
  pages={500-514}
}
  • Nir Shlezinger, M. Chen, +2 authors Shuguang Cui
  • Published 2021
  • Computer Science, Mathematics
  • IEEE Transactions on Signal Processing
  • Traditional deep learning models are trained at a centralized server using data samples collected from users. Such data samples often include private information, which the users may not be willing to share. Federated learning (FL) is an emerging approach to train such learning models without requiring the users to share their data. FL consists of an iterative procedure, where in each iteration the users train a copy of the learning model locally. The server then collects the individual updates… CONTINUE READING
    11 Citations

    Figures from this paper

    Over-the-Air Federated Learning from Heterogeneous Data
    • 6
    • PDF
    Bayesian Federated Learning over Wireless Networks
    • PDF
    Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications
    • 10
    • PDF
    Task-Based Analog-to-Digital Converters
    • 2
    • PDF
    FedRec: Federated Learning of Universal Receivers over Fading Channels
    • 1
    • PDF

    References

    SHOWING 1-10 OF 61 REFERENCES
    Federated Learning with Quantization Constraints
    • 12
    Over-the-Air Federated Learning from Heterogeneous Data
    • 6
    • PDF
    The Communication-Aware Clustered Federated Learning Problem
    • 4
    Communication-Efficient Learning of Deep Networks from Decentralized Data
    • 1,806
    • Highly Influential
    • PDF
    Federated Learning via Over-the-Air Computation
    • 146
    • PDF
    Update Aware Device Scheduling for Federated Learning at the Wireless Edge
    • 20
    • PDF
    On the Convergence of FedAvg on Non-IID Data
    • 207
    • Highly Influential
    • PDF
    Reliable Federated Learning for Mobile Networks
    • 33
    • PDF