mlsanityData to 7 Oct 2026

Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning

arXiv 1911.04655 ↗First posted 12 Nov 2019cs.LG cs.IR stat.MLcited by 18

Not on the map. Why?

Abstract (arXiv)

The high cost of communicating gradients is a major bottleneck for federated learning, as the bandwidth of the participating user devices is limited. Existing gradient compression algorithms are mainly designed for data centers with high-speed network and achieve O(√d log d) per-iteration communication cost at best, where d is the size of the model. We propose hyper-sphere quantization (HSQ), a general framework that can be configured to achieve a continuum of trade-offs between communication efficiency and gradient accuracy. In particular, at the high compression ratio end, HSQ provides a low per-iteration communication cost of O(log d), which is favorable for federated learning. We prove the convergence of HSQ theoretically and show by experiments that HSQ significantly reduces the communication cost of model training without hurting convergence accuracy.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 3; 2023: 3; 2024: 3; 2025: 0; 2026: 1.

18 papers.

Sort:

  1. 2021Personalized Federated Learning using Hypernetworkscited by 210
  2. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  3. 2021Personalized Federated Learning with Gaussian Processescited by 76
  4. 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
  5. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  6. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  7. 2022Federated Learning with Heterogeneous Architectures using Graph HyperNetworkscited by 17
  8. 2023A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regretcited by 7
  9. 2024Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attackscited by 7
  10. 2023Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clusteringcited by 5
  11. 2021Sparse Personalized Federated Learningcited by 4
  12. 2022Sparse Federated Learning with Hierarchical Personalized Modelscited by 4
6 more
  1. 2021Towards Heterogeneous Clients with Elastic Federated Learningcited by 2
  2. 2021A Personalized Federated Learning Algorithm: an Application in Anomaly Detectioncited by 1
  3. 2024FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantizationcited by 1
  4. 2024FedFT: Improving Communication Performance for Federated Learning with Frequency Space Transformationcited by 1
  5. 2023RS-DGC: Exploring Neighborhood Statistics for Dynamic Gradient Compression on Remote Sensing Image Interpretationcited by 0
  6. 2026Quantization in Federated Learning: Methods, Challenges and Future Directionscited by 0