pith. sign in

arxiv: 2606.26822 · v1 · pith:G6VOJXELnew · submitted 2026-06-25 · 💻 cs.LG

Quantization in Federated Learning: Methods, Challenges and Future Directions

Farwa Ikram , Dipanwita Thakur , Antonella Guzzo , Giancarlo Fortino This is my paper

Pith reviewed 2026-06-26 04:53 UTC · model grok-4.3

classification 💻 cs.LG
keywords federated learningquantizationsystematic reviewclient heterogeneitynon-IID dataprivacy preservationedge computingcommunication efficiency
0
0 comments X

The pith

Quantization in federated learning must be treated as a systems component that interacts with client drift, partial participation, and privacy mechanisms, not just as a compression technique.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents the first systematic review of quantization methods specifically tailored to federated learning. It organizes these methods using a taxonomy based on six FL-specific dimensions: client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization. The review examines how quantization affects core FL behaviors like client drift and convergence stability. It identifies open research gaps and provides design guidelines for deploying quantized FL on resource-constrained devices. This approach highlights quantization's role in addressing communication bottlenecks and device limitations in privacy-preserving distributed training.

Core claim

The paper claims to be the first FL-centric systematic review that introduces a novel taxonomy for quantization methods organized around FL-specific dimensions including client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization, while analyzing interactions with FL behaviors such as client drift, partial participation, convergence stability, secure aggregation, and differential privacy.

What carries the argument

A novel taxonomy for quantization in FL organized around six FL-specific dimensions that captures how quantization methods address client heterogeneity, aggregation consistency, and related challenges.

If this is right

  • Quantization methods can be assessed for their robustness to non-IID data distributions in federated settings.
  • Design choices in quantization must consider integration with secure aggregation protocols.
  • Hardware and energy co-optimization becomes a key factor in selecting quantization strategies for edge devices.
  • Communication scheduling can be adapted based on quantization levels to improve overall FL efficiency.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Practitioners could use the taxonomy to select quantization methods that balance privacy and performance in specific FL deployments.
  • Future work might extend the taxonomy to include emerging FL variants like vertical federated learning.
  • The analysis suggests that ignoring FL-specific dimensions in quantization could lead to suboptimal convergence in heterogeneous environments.

Load-bearing premise

The review assumes that all existing quantization methods in federated learning can be meaningfully captured and organized by the six proposed FL-specific dimensions without significant omissions.

What would settle it

Discovery of a quantization technique used in federated learning that cannot be classified under any of the six dimensions of client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, or hardware/energy co-optimization.

Figures

Figures reproduced from arXiv: 2606.26822 by Antonella Guzzo, Dipanwita Thakur, Farwa Ikram, Giancarlo Fortino.

Figure 1
Figure 1. Figure 1: Structure of the Survey and trade-offs (RQ2), while Section 5 highlights key research gaps (RQ3). Section 6 presents promising future research directions (RQ4). Finally, Sections 7 and 8 provide an integrated discussion and concluding remarks. 2 Research Methodology 2.1 Objective The proposed work is a systematic literature review (SLR) using PRISMA (Preferred Reporting Items for Systematic Reviews) [84]. … view at source ↗
Figure 3
Figure 3. Figure 3: Design Dimensions for Quantization Taxonomy in FL [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
read the original abstract

Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data. Quantization is one of the most effective mechanisms for mitigating these limitations, reducing both uplink/downlink payloads and on-device computation. This paper provides the first FL-centric systematic review of quantization, introducing a novel taxonomy organized around FL-specific dimensions, including client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization. Beyond cataloging existing methods, we analyze how quantization interacts with core FL behaviors such as client drift, partial participation, convergence stability, secure aggregation, and differential privacy. We further identify cross-method insights, open research gaps, and design guidelines for practitioners deploying quantized FL on mobile, IoT, and edge platforms. This survey thus establishes quantization not merely as a compression technique, but as a fundamental systems component shaping the performance, robustness, and practicality of modern FL.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. This manuscript is a systematic literature survey on quantization techniques applied to Federated Learning (FL). It claims to be the first FL-centric review, proposing a novel taxonomy organized around six FL-specific dimensions (client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization). The paper catalogs existing methods, analyzes interactions with FL phenomena such as client drift, partial participation, convergence, secure aggregation, and differential privacy, identifies cross-method insights and research gaps, and offers design guidelines for deployment on mobile/IoT/edge platforms.

Significance. If the taxonomy successfully organizes the literature without major omissions and the interaction analysis yields actionable insights, the survey could become a useful reference for the FL community. The emphasis on FL-specific dimensions rather than generic quantization categories is a potential strength, as is the explicit treatment of how quantization affects core FL behaviors. Reproducible aspects are limited to the survey methodology itself; no machine-checked proofs or code artifacts are mentioned.

minor comments (3)
  1. [Abstract] Abstract: the claim of being the 'first FL-centric systematic review' would benefit from a brief footnote or sentence contrasting the scope against the closest prior surveys on FL compression or quantization (e.g., those focused on general model compression).
  2. [Taxonomy section (inferred from abstract)] The six taxonomy dimensions are introduced in the abstract and presumably detailed in the main taxonomy section; a short table mapping each dimension to the specific FL challenges it addresses would improve readability and help readers quickly locate relevant methods.
  3. [Future directions / gaps section] The discussion of open research gaps is valuable but would be strengthened by indicating, for each gap, whether it is primarily a methodological, empirical, or systems-integration issue.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the constructive review and the recommendation of minor revision. The report accurately summarizes the manuscript's contributions and does not raise any specific major comments or concerns requiring detailed rebuttal.

Circularity Check

0 steps flagged

No significant circularity in survey structure

full rationale

This is a literature survey paper whose central contribution is a taxonomy organizing existing external quantization methods in FL. No derivations, equations, fitted parameters, predictions, or self-citation chains appear in the provided abstract or description. The taxonomy is presented as an organizational framework for prior work rather than a derived result that reduces to its own inputs. All content references external literature without load-bearing self-referential steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a literature survey paper. It introduces no free parameters, mathematical axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5722 in / 1107 out tokens · 37672 ms · 2026-06-26T04:53:39.586790+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

141 extracted references · 21 canonical work pages · 5 internal anchors

  1. [1]

    Abdelmoniem and Marco Canini

    Ahmed M. Abdelmoniem and Marco Canini. 2021. Towards Mitigating Device Heterogeneity in Federated Learning via Adaptive Model Quantization. InProceedings of the 1st Workshop on Machine Learning and Systems(Online, United Kingdom)(EuroMLSys ’21). Association for Computing Machinery, New York, NY, USA, 96–103

    2021

  2. [2]

    Mohammed Aledhari, Rehma Razzak, Reza M Parizi, and Fahad Saeed. 2020. Federated learning: A survey on enabling technologies, protocols, and applications.IEEE Access8 (2020), 140699–140725

    2020

  3. [3]

    Li, Ryota Tomioka, and Milan Vojnovic

    Dan Alistarh, Demjan Grubic, Jerry Z. Li, Ryota Tomioka, and Milan Vojnovic. 2017. QSGD: communication-efficient SGD via gradient quantization and encoding. InProceedings of the 31st International Conference on Neural Information Processing Systems(Long Beach, California, USA)(NIPS’17). 1707–1718

    2017

  4. [4]

    Omair Rashed Abdulwareth Almanifi, Chee-Onn Chow, Mau-Luen Tham, Joon Huang Chuah, and Jeevan Kanesan. 2023. Communication and computation efficiency in federated learning: A survey.Internet of Things22 (2023), 100742

    2023

  5. [5]

    Kulkarni, and H

    Mohammad Mohammadi Amiri, Deniz Gunduz, Sanjeev R. Kulkarni, and H. Vincent Poor. 2020. Federated Learning With Quantized Global Model Updates. arXiv:2006.10672 [cs.IT] https://arxiv.org/abs/2006.10672

    work page arXiv 2020

  6. [6]

    Emre Ardiç and Yakup Genç. 2025. Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning With Adaptive Quantization and Differential Privacy.IEEE Access13 (2025), 54322–54337

    2025

  7. [7]

    Hesham Ayman, Shaimaa Haridy, Yasmine M Afify, and Walaa Gad. 2026. FedEnsemble: federated learning model for efficient sentiment analysis. Computing108, 1 (2026), 11. Manuscript submitted to ACM Quantization in Federated Learning: Methods, Challenges and Future Directions 31

    2026

  8. [8]

    Seyed Mohammad Azimi-Abarghouyi and Carlo Fischione. 2025. Multi-Layer Hierarchical Federated Learning with Quantization.arXiv preprint arXiv:2505.08145(2025)

    work page arXiv 2025

  9. [9]

    Arian Bakhtiarnia, Nemanja Milošević, Qi Zhang, Dragana Bajović, and Alexandros Iosifidis. 2022. Dynamic Split Computing for Efficient Deep Edge Intelligence. arXiv:2205.11269 [cs.CV] https://arxiv.org/abs/2205.11269

    work page arXiv 2022

  10. [10]

    Ron Banner, Yury Nahshan, and Daniel Soudry. 2019. Post training 4-bit quantization of convolutional networks for rapid-deployment. InAdvances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc., Article 714, 9 pages

    2019

  11. [11]

    Yoshua Bengio, Nicholas Léonard, and Aaron Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. InarXiv preprint arXiv:1308.3432

    work page internal anchor Pith review Pith/arXiv arXiv 2013

  12. [12]

    Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth

    Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017. Practical Secure Aggregation for Privacy-Preserving Machine Learning. InProceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security(Dallas, Texas, USA)(CCS ’17). 1175–1191

    2017

  13. [13]

    Pavlos S Bouzinis, Panagiotis D Diamantoulakis, and George K Karagiannidis. 2023. Wireless quantized federated learning: A joint computation and communication design.IEEE Transactions on Communications71, 5 (2023), 2756–2770

    2023

  14. [14]

    Zavareh Bozorgasl and Hao Chen. 2025. Communication-Efficient Federated Learning via Clipped Uniform Quantization. In59th Annual Conference on Information Sciences and Systems (CISS). IEEE, 1–6

    2025

  15. [15]

    Sebastian Caldas, Peter Wu, Tian Li, Jakub Konečný, Brendan McMahan, Virginia Smith, and Ameet Talwalkar. 2018. LEAF: A Benchmark for Federated Settings. InProceedings of the 2nd Workshop on Federated Learning for Data Privacy and Confidentiality

    2018

  16. [16]

    Guojun Chen, Kaixuan Xie, Yuheng Tu, Tiecheng Song, Yinfei Xu, Jing Hu, and Lun Xin. 2024. NQFL: Nonuniform Quantization for Communication Efficient Federated Learning.IEEE Communications Letters28, 2 (2024), 332–336

    2024

  17. [17]

    Huancheng Chen and Haris Vikalo. 2024. Mixed-precision quantization for federated learning on resource-constrained heterogeneous devices. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6138–6148

    2024

  18. [18]

    Huiqiang Chen, Tianqing Zhu, Tao Zhang, Wanlei Zhou, and Philip S. Yu. 2023. Privacy and Fairness in Federated Learning: On the Perspective of Tradeoff.ACM Comput. Surv.56, 2, Article 39 (Sept. 2023), 37 pages

    2023

  19. [19]

    Li Chen, Wei Liu, Yunfei Chen, and Weidong Wang. 2024. Communication-efficient design for quantized decentralized federated learning.IEEE Transactions on Signal Processing72 (2024), 1175–1188

    2024

  20. [20]

    Longfei Chen, Zhenyu Wu, and Yang Ji. 2023. Two-Stage Adaptive Gradient Quantization in Federated Learning. In2023 8th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC). IEEE, 441–445

    2023

  21. [21]

    Mingzhe Chen, Nir Shlezinger, H Vincent Poor, Yonina C Eldar, and Shuguang Cui. 2021. Communication-efficient federated learning.Proceedings of the National Academy of Sciences118, 17 (2021), e2024789118

    2021

  22. [22]

    Shengbo Chen, Le Li, Guanghui Wang, Meng Pang, and Cong Shen. 2023. Federated learning with heterogeneous quantization bit allocation and aggregation for internet of things.IEEE Internet of Things Journal11, 2 (2023), 3132–3143

    2023

  23. [23]

    Zichao Chen and Jun Zhang. 2025. Efficient Communication Method for Hierarchical Federated Learning Based on 1-Bit Compressed Sensing. In 5th International Conference on Consumer Electronics and Computer Engineering (ICCECE). IEEE, 675–678

    2025

  24. [24]

    Jungwook Choi, Kailash Gopalakrishnan, Swagath Venkataramani, and Vijayalakshmi Srinivasan. 2021. A Survey on Mixed-Precision Quantization for Deep Neural Networks.IEEE Transactions on Neural Networks and Learning Systems33, 4 (2021), 1452–1468

    2021

  25. [25]

    Jungwook Choi, Zhuo Wang, Swagath Venkataramani, Po-Han Chuang, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. PACT: Parameterized Clipping Activation for Quantized Neural Networks. InProceedings of the European Conference on Computer Vision (ECCV). 730–746

    2018

  26. [26]

    J. H. Conway and N. J. A. Sloane. 1999.Sphere Packings, Lattices and Groups. Springer

    1999

  27. [27]

    Xinyan Dai, Xiao Yan, Kaiwen Zhou, Han Yang, Kelvin KW Ng, James Cheng, and Yu Fan. 2019. Hyper-sphere quantization: Communication-efficient sgd for federated learning.arXiv preprint arXiv:1911.04655(2019)

    work page arXiv 2019

  28. [28]

    de Lamare, and Vítor H

    Alireza Danaee, Rodrigo C. de Lamare, and Vítor H. Nascimento. 2022. Quantization-Aware Federated Learning with Coarsely Quantized Measurements. In30th European Signal Processing Conference (EUSIPCO). 1691–1695

    2022

  29. [29]

    Mahoney, and Kurt Keutzer

    Zhen Dong, Zhewei Yao, Amir Gholami, Michael W. Mahoney, and Kurt Keutzer. 2019. HAWQ: Hessian Aware Quantization of Neural Networks With Mixed-Precision. InProceedings of the IEEE International Conference on Computer Vision (ICCV). 293–302

    2019

  30. [30]

    Qiang Duan, Jun Huang, Shijing Hu, Ruijun Deng, Zhihui Lu, and Shui Yu. 2023. Combining Federated Learning and Edge Computing Toward Ubiquitous Intelligence in 6G Network: Challenges, Recent Advances, and Future Directions.IEEE Communications Surveys & Tutorials25, 4 (2023), 2892–2950

    2023

  31. [31]

    Praveer Dubey and Mohit kumar. 2024. Quantization Strategies in Federated Learning: Comparative Assessment of Methods and Challenges. (Aug. 2024). https://doi.org/10.36227/techrxiv.172503571.10768521/v1

    work page doi:10.36227/techrxiv.172503571.10768521/v1 2024

  32. [32]

    Anis Elgabli. 2025. PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning.IEEE Open Journal of the Communications Society6 (2025), 4156–4175

    2025

  33. [33]

    Ahmed Roushdy Elkordy and A Salman Avestimehr. 2022. HeteroSAg: Secure aggregation with heterogeneous quantization in federated learning. IEEE Transactions on Communications70, 4 (2022), 2372–2386

    2022

  34. [34]

    Esser, Jeffrey L

    Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Raja Appuswamy, and Dharmendra S. Modha. 2020. Learned Step Size Quantization. In ICLR. Manuscript submitted to ACM 32 Ikram et al

    2020

  35. [35]

    Xiang Fang, Li Chen, Huarui Yin, Xiaohui Chen, and Weidong Wang. 2026. Communication Efficient Federated Learning With Quantization-Aware Training Design.IEEE Transactions on Machine Learning in Communications and Networking4 (2026), 45–59

    2026

  36. [36]

    Wenjun Feng and Xian Zhang. 2022. Wireless federated learning with dynamic quantization and bandwidth adaptation.IEEE Wireless Communica- tions Letters11, 11 (2022), 2335–2339

    2022

  37. [37]

    Jonas Geiping, Hartmut Bauermeister, Hannah Dröge, and Michael Moeller. 2020. Inverting gradients - how easy is it to break privacy in federated learning?. InProceedings of the 34th International Conference on Neural Information Processing Systems(Vancouver, BC, Canada)(NIPS ’20). Article 1421, 11 pages

    2020

  38. [38]

    Mahoney, and Kurt Keutzer

    Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, and Kurt Keutzer. 2021. A Survey of Quantization Methods for Efficient Neural Network Inference. arXiv:2103.13630 [cs.CV] https://arxiv.org/abs/2103.13630

    work page arXiv 2021

  39. [39]

    Shinya Gongyo, Jinrong Liang, Mitsuru Ambai, Rei Kawakami, and Ikuro Sato. 2024. Learning Non-Uniform Step Sizes for Neural Network Quantization. InProceedings of the Asian Conference on Computer Vision (ACCV). 4385–4402

    2024

  40. [40]

    Kartik Gupta, Marios Fournarakis, Matthias Reisser, Christos Louizos, and Markus Nagel. 2023. Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices.Transactions on Machine Learning Research(2023)

    2023

  41. [41]

    Shayan Mohajer Hamidi and Ali Bereyhi. 2025. Rate-Constrained Quantization for Communication-Efficient Federated Learning. InICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 1–5

    2025

  42. [42]

    Song Han, Huizi Mao, and William J. Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.International Conference on Learning Representations (ICLR)(2016)

    2016

  43. [43]

    Muhammad Abdullah Hanif, Giuseppe Maria Sarda, Alberto Marchisio, Guido Masera, Maurizio Martina, and Muhammad Shafique. 2022. CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networks. In 2022 International Joint Conference on Neural Networks (IJCNN). 1–8

    2022

  44. [44]

    Nan He, Yiming Chen, Zheng Jiang, Song Yang, and Lifeng Sun. 2025. DynFed: Adaptive Federated Learning via Quantization-Aware Knowledge Distillation. InProceedings of the 33rd ACM International Conference on Multimedia(Dublin, Ireland)(MM ’25). Association for Computing Machinery, New York, NY, USA, 11844–11852

    2025

  45. [45]

    Zixiao He, Gengming Zhu, Shaobo Zhang, Entao Luo, and Yijiang Zhao. 2025. FedDT: A Communication-Efficient Federated Learning via Knowledge Distillation and Ternary Compression.Electronics14, 11 (2025), 2183

    2025

  46. [46]

    Robert Hönig, Yiren Zhao, and Robert Mullins. 2022. DAdaQuant: Doubly-adaptive quantization for communication-efficient federated learning. In International Conference on Machine Learning. PMLR, 8852–8866

    2022

  47. [47]

    Benoit Jacob, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko. 2018. Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2704–2713

    2018

  48. [48]

    Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical Reparameterization with Gumbel-Softmax. InProceedings of the International Conference on Learning Representations (ICLR)

    2017

  49. [49]

    Herve Jégou, Matthijs Douze, and Cordelia Schmid. 2011. Product Quantization for Nearest Neighbor Search.IEEE Transactions on Pattern Analysis and Machine Intelligence33, 1 (2011), 117–128

    2011

  50. [50]

    Divyansh Jhunjhunwala, Advait Gadhikar, Gauri Joshi, and Yonina C Eldar. 2021. Adaptive quantization of model updates for communication- efficient federated learning. InIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 3110–3114

    2021

  51. [51]

    Yu Ji and Lan Chen. 2022. FedQNN: A computation–communication-efficient federated learning framework for IoT with low-bitwidth neural network quantization.IEEE Internet of Things Journal10, 3 (2022), 2494–2507

    2022

  52. [52]

    Ninghui Jia, Zhihao Qu, Baoliu Ye, Yanyan Wang, Shihong Hu, and Song Guo. 2025. A Comprehensive Survey on Communication-Efficient Federated Learning in Mobile Edge Environments.IEEE Communications Surveys & Tutorials(2025), 1–1

    2025

  53. [53]

    Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawit, Zachary Charles, Graham Cormode, et al

    Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawit, Zachary Charles, Graham Cormode, et al. 2021

    2021

  54. [54]

    Khan, Walid Saad, Zhu Han, Ekram Hossain, and Choong Seon Hong

    Latif U. Khan, Walid Saad, Zhu Han, Ekram Hossain, and Choong Seon Hong. 2021. Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges.IEEE Communications Surveys & Tutorials23, 3 (2021), 1759–1799

    2021

  55. [55]

    Ansam Khraisat, Ammar Alazab, Sarabjot Singh, Tony Jan, and Alfredo Jr. Gomez. 2024. Survey on Federated Learning for Intrusion Detection System: Concept, Architectures, Aggregation Strategies, Challenges, and Future Directions.ACM Comput. Surv.57, 1, Article 7 (Oct. 2024), 38 pages

    2024

  56. [56]

    Minsu Kim, Walid Saad, Mohammad Mozaffari, and Merouane Debbah. 2022. On the tradeoff between energy, precision, and accuracy in federated quantized neural networks. InIEEE International Conference on Communications. IEEE, 2194–2199

    2022

  57. [57]

    Seung-Wook Kim, Seongyeol Kim, Jiah Kim, Seowon Ji, and Se-Ho Lee. 2025. FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization. arXiv:2506.23516 [cs.LG] https://arxiv.org/abs/2506.23516

    work page arXiv 2025

  58. [58]

    You Jun Kim and Choong Seon Hong. 2020. Optimized quantization for convolutional deep neural networks in federated learning. In21st Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE, 150–154

    2020

  59. [59]

    Federated Learning: Strategies for Improving Communication Efficiency

    Jakub Konečný, H. Brendan McMahan, Felix X. Yu, Peter Richtárik, Ananda Theertha Suresh, and Dave Bacon. 2017. Federated Learning: Strategies for Improving Communication Efficiency. arXiv:1610.05492 [cs.LG] https://arxiv.org/abs/1610.05492

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  60. [60]

    Raghuraman Krishnamoorthi. 2018. Quantizing Deep Convolutional Networks for Efficient Inference: A Whitepaper.arXiv preprint arXiv:1806.08342 (2018). Manuscript submitted to ACM Quantization in Federated Learning: Methods, Challenges and Future Directions 33

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  61. [61]

    Kummari Naveen Kumar, Chalavadi Krishna Mohan, and Linga Reddy Cenkeramaddi. 2024. The Impact of Adversarial Attacks on Federated Learning: A Survey.IEEE Transactions on Pattern Analysis and Machine Intelligence46, 5 (2024), 2672–2691

    2024

  62. [62]

    Natalie Lang, Elad Sofer, Tomer Shaked, and Nir Shlezinger. 2023. Joint privacy enhancement and quantization in federated learning.IEEE Transactions on Signal Processing71 (2023), 295–310

    2023

  63. [63]

    Sangmin Lee and Hyeryung Jang. 2025. BiPruneFL: Computation and Communication Efficient Federated Learning With Binary Quantization and Pruning.IEEE Access13 (2025), 42441–42456

    2025

  64. [64]

    Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2020. Additive Powers-of-Two Quantization: An Efficient Non-Uniform Discretization for Neural Networks. InICLR

    2020

  65. [65]

    Tian Li, Anit Kumar Sahu, Ameet Talwalkar, and Virginia Smith. 2020. Federated learning: Challenges, methods, and future directions.IEEE signal processing magazine37, 3 (2020), 50–60

    2020

  66. [66]

    Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2019. Federated Optimization in Heterogeneous Networks. InProceedings of the 1st Adaptive & Multitask Learning Workshop, Long Beach, California, 2019

    2019

  67. [67]

    Yangchen Li, Ying Cui, and Vincent Lau. 2024. GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing Systems.IEEE Transactions on Wireless Communications23, 7 (2024), 6856–6872

    2024

  68. [68]

    Yifei Li, Yijia Guo, Mamoun Alazab, Shengbo Chen, Cong Shen, and Keping Yu. 2022. Joint optimal quantization and aggregation of federated learning scheme in VANETs.IEEE Transactions on Intelligent Transportation Systems23, 10 (2022), 19852–19863

    2022

  69. [69]

    Yawen Li, Wenling Li, and Zhe Xue. 2022. Federated learning with stochastic quantization.International Journal of Intelligent Systems37, 12 (2022), 11600–11621

    2022

  70. [70]

    Zirui Lian, Jing Cao, Yanru Zuo, Weihong Liu, and Zongwei Zhu. 2021. AGQFL: communication-efficient federated learning via automatic gradient quantization in edge heterogeneous systems. In2021 IEEE 39th International Conference on Computer Design (ICCD). IEEE, 551–558

    2021

  71. [71]

    Wei Yang Bryan Lim, Nguyen Cong Luong, Dinh Thai Hoang, Yutao Jiao, Ying-Chang Liang, Qiang Yang, Dusit Niyato, and Chunyan Miao. 2020. Federated learning in mobile edge networks: A comprehensive survey.IEEE communications surveys & tutorials22, 3 (2020), 2031–2063

    2020

  72. [72]

    Xiaohan Lin, Yuan Liu, and Fangjiong Chen. 2021. Channel-adaptive quantization for wireless federated learning. In2021 IEEE/CIC International Conference on Communications in China (ICCC). IEEE, 457–462

    2021

  73. [73]

    Yujun Lin, Song Han, Huizi Mao, Yu Wang, and William Dally. 2018. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. InInternational Conference on Learning Representations (ICLR)

    2018

  74. [74]

    Heting Liu, Fang He, and Guohong Cao. 2023. Communication-efficient federated learning for heterogeneous edge devices based on adaptive gradient quantization. InIEEE INFOCOM 2023-IEEE Conference on Computer Communications. IEEE, 1–10

    2023

  75. [75]

    Ji Liu, Jizhou Huang, Yang Zhou, Xuhong Li, Shilei Ji, Haoyi Xiong, and Dejing Dou. 2022. From distributed machine learning to federated learning: A survey.Knowledge and Information Systems64, 4 (2022), 885–917

    2022

  76. [76]

    Xiaonan Liu, Yansha Deng, Arumugam Nallanathan, and Mehdi Bennis. 2024. Federated Learning and Meta Learning: Approaches, Applications, and Directions.IEEE Communications Surveys & Tutorials26, 1 (2024), 571–618

    2024

  77. [77]

    Yi Liu, Xingliang Yuan, Zehui Xiong, Jiawen Kang, Xiaofei Wang, and Dusit Niyato. 2020. Federated learning for 6G communications: Challenges, methods, and future directions.China Communications17, 9 (2020), 105–118

    2020

  78. [78]

    Sin Kit Lo, Qinghua Lu, Chen Wang, Hye-Young Paik, and Liming Zhu. 2021. A systematic literature review on federated machine learning: From a software engineering perspective.Comput. Surveys54, 5 (2021), 1–39

    2021

  79. [79]

    2020.Threats to Federated Learning

    Lingjuan Lyu, Han Yu, Jun Zhao, and Qiang Yang. 2020.Threats to Federated Learning. Springer International Publishing, Cham, 3–16

    2020

  80. [80]

    Yuzhu Mao, Zihao Zhao, Guangfeng Yan, Yang Liu, Tian Lan, Linqi Song, and Wenbo Ding. 2022. Communication-efficient federated learning with adaptive quantization.ACM Transactions on Intelligent Systems and Technology (TIST)13, 4 (2022), 1–26

    2022

Showing first 80 references.