mlsanityData to 14 Oct 2026

HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks

arXiv 2204.06760 ↗First posted 14 Apr 2022cs.LG cs.AI cs.DCcited by 12

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a new artificial intelligence concept that enables Internet-of-Things (IoT) devices to learn a collaborative model without sending the raw data to centralized nodes for processing. Despite numerous advantages, low computing resources at IoT devices and high communication costs for exchanging model parameters make applications of FL in massive IoT networks very limited. In this work, we develop a novel compression scheme for FL, called high-compression federated learning (HCFL), for very large scale IoT networks. HCFL can reduce the data load for FL processes without changing their structure and hyperparameters. In this way, we not only can significantly reduce communication costs, but also make intensive learning processes more adaptable on low-computing resource IoT devices. Furthermore, we investigate a relationship between the number of IoT devices and the convergence level of the FL model and thereby better assess the quality of the FL process. We demonstrate our HCFL scheme in both simulations and mathematical analyses. Our proposed theoretical research can be used as a minimum level of satisfaction, proving that the FL process can achieve good performance when a determined configuration is met. Therefore, we show that HCFL is applicable in any FL-integrated networks with numerous IoT devices.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 21 of its 51 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

21 of 51 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  4. 2016Deep Variational Information Bottleneckcited by 930
  5. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  7. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
  8. 2016Trained Ternary Quantizationcited by 208
  9. 2016Ternary Weight Networkscited by 204
  10. 2019Federated Learning over Wireless Fading Channelscited by 183
  11. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  12. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
9 more
  1. 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 145
  2. 2021Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challengescited by 76
  3. 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
  4. 2021What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligencecited by 50
  5. 2019Federated Learning with Autotuned Communication-Efficient Secure Aggregationcited by 23
  6. 2020Massive Access for 5G and Beyondcited by 23
  7. 2019Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challengescited by 19
  8. 2018Autoencoder based image compression: can the learning be quantization independent?cited by 8
  9. 2018Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep learningcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 2; 2025: 5.

12 papers.

  1. 2024Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Surveycited by 9
  2. 2023Distortion Resilience for Goal-Oriented Semantic Communicationcited by 4
  3. 2022Label driven Knowledge Distillation for Federated Learning with non-IID Datacited by 3
  4. 2023Collaborative Policy Learning for Dynamic Scheduling Tasks in Cloud-Edge-Terminal IoT Networks Using Federated Reinforcement Learningcited by 3
  5. 2022Resource Allocation for Compression-aided Federated Learning with High Distortion Ratecited by 2
  6. 2023Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Controlcited by 1
  7. 2024Personalized Federated Learning for Generative AI-Assisted Semantic Communicationscited by 1
  8. 2025Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coresetcited by 1
  9. 2025Communication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptationcited by 1
  10. 2025Knowledge Abstraction for Knowledge-based Semantic Communication: A Generative Causality Invariant Approachcited by 0
  11. 2025D2D Power Allocation via Quantum Graph Neural Networkcited by 0
  12. 2025Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Researchcited by 0