mlsanityData to 14 Oct 2026

FedHQ: Hybrid Runtime Quantization for Federated Learning

arXiv 2505.11982 ↗First posted 17 May 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a decentralized model training approach that preserves data privacy but struggles with low efficiency. Quantization, a powerful training optimization technique, has been widely explored for integration into FL. However, many studies fail to consider the distinct performance attribution between particular quantization strategies, such as post-training quantization (PTQ) or quantization-aware training (QAT). As a result, existing FL quantization methods rely solely on either PTQ or QAT, optimizing for speed or accuracy while compromising the other. To efficiently accelerate FL and maintain distributed convergence accuracy across various FL settings, this paper proposes a hybrid quantitation approach combining PTQ and QAT for FL systems. We conduct case studies to validate the effectiveness of using hybrid quantization in FL. To solve the difficulty of modeling speed and accuracy caused by device and data heterogeneity, we propose a hardware-related analysis and data-distribution-related analysis to help identify the trade-off boundaries for strategy selection. Based on these, we proposed a novel framework named FedHQ to automatically adopt optimal hybrid strategy allocation for FL systems. Specifically, FedHQ develops a coarse-grained global initialization and fine-grained ML-based adjustment to ensure efficiency and robustness. Experiments show that FedHQ achieves up to 2.47x times training acceleration and up to 11.15% accuracy improvement and negligible extra overhead.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

29 of 40 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  4. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  6. 2018Federated Learning with Non-IID Datacited by 1,108
  7. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  8. 2023LLM-QAT: Data-Free Quantization Aware Training for Large Language Modelscited by 324
  9. 2021Post-Training Quantization for Vision Transformercited by 278
  10. 2022Post-training Quantization on Diffusion Modelscited by 267
  11. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  12. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
17 more
  1. 2022On-Device Training Under 256KB Memorycited by 160
  2. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 127
  3. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  4. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  5. 2013Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networkscited by 84
  6. 2017Adaptive Quantization for Deep Neural Networkcited by 67
  7. 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Designcited by 47
  8. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  9. 2024A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithmscited by 31
  10. 2021Equality Saturation for Tensor Graph Superoptimizationcited by 27
  11. 2022Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devicescited by 12
  12. 2021Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPUcited by 9
  13. 2024A Survey on Federated Learning in Intelligent Transportation Systemscited by 9
  14. 2024FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantizationcited by 5
  15. 2022Hierarchical Federated Learning with Privacycited by 4
  16. 2024FedFQ: Federated Learning with Fine-Grained Quantizationcited by 3
  17. 2024Quantized and Asynchronous Federated Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Quantization Impact on the Accuracy and Communication Efficiency Trade-off in Federated Learning for Aerospace Predictive Maintenancecited by 0
  2. 2026Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices
  2. 2025FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
  3. 2026Quantization in Federated Learning: Methods, Challenges and Future Directions
  4. 2023Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity
  5. 2021FedDQ: Communication-Efficient Federated Learning with Descending Quantization
  6. 2022Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks
  7. 2025FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning
  8. 2025Privacy-Preserving Quantized Federated Learning with Diverse Precision