mlsanityData to 7 Oct 2026

Time-sensitive Learning for Heterogeneous Federated Edge Intelligence

arXiv 2301.10977 ↗First posted 26 Jan 2023cs.LG cs.NIcited by 8

Not on the map. Why?

Abstract (arXiv)

Real-time machine learning has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. We investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow slow-performance edge servers to be removed from participating in model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, local epoch number. We develop an analytical expression to characterize the impact of staleness effect of asynchronous coordination and straggler effect of FL on the time consumption of TS-FL-ASC. Experimental results show that TS-FL-SC and TS-FL-ASC can provide up to 63% and 28% of reduction, in the overall model training time, respectively.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 59 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

34 of 59 references.

References · 34

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2017Federated Multi-Task Learningcited by 669
  6. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  8. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  9. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  10. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  11. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  12. 2019Asynchronous Federated Optimizationcited by 264
22 more
  1. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
  2. 2018Federated Learning via Over-the-Air Computationcited by 215
  3. 2019Adaptive Gradient-Based Meta-Learning Methodscited by 183
  4. 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 80
  5. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  6. 2019Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligencecited by 75
  7. 2019Variational Federated Multi-Task Learningcited by 69
  8. 2020Cost-Effective Federated Learning Designcited by 61
  9. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 56
  10. 2020From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problemscited by 51
  11. 2019Semi-Cyclic Stochastic Gradient Descentcited by 40
  12. 2022Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoningcited by 16
  13. 2020Distributed Optimization for Energy-efficient Fog Computing in the Tactile Internetcited by 14
  14. 2020Towards Self-learning Edge Intelligence in 6Gcited by 14
  15. 2022Rate-Distortion Theory for Strategic Semantic Communicationcited by 12
  16. 2021How to decay your learning ratecited by 11
  17. 2023Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networkscited by 11
  18. 2022Reasoning on the Air: An Implicit Semantic Communication Architecturecited by 9
  19. 2017Real-Time Machine Learning: The Missing Piecescited by 7
  20. 2021AdaptiveFog: A Modelling and Optimization Framework for Fog Computing in Intelligent Transportation Systemscited by 4
  21. 2019Optimal Mini-Batch Size Selection for Fast Gradient Descentcited by 3
  22. 2020Optimizing Resource-Efficiency for Federated Edge Intelligence in IoT Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 3; 2026: 1.

8 papers.

  1. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  2. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  3. 2024Towards Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approachcited by 6
  4. 2023Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approachcited by 3
  5. 2023Towards Net-Zero Carbon Emissions in Network AI for 6G and Beyondcited by 3
  6. 2025The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligencecited by 1
  7. 2025Robust Federated Learning against Model Perturbation in Edge Networkscited by 0
  8. 2026Client and Training Data Selection for Computationally Efficient Synchronized Federated Learningcited by 0