mlsanityData to 14 Oct 2026

Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices

arXiv 2310.13981 ↗First posted 21 Oct 2023cs.LG cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

Distributed Artificial Intelligence (AI) model training over mobile edge networks encounters significant challenges due to the data and resource heterogeneity of edge devices. The former hampers the convergence rate of the global model, while the latter diminishes the devices' resource utilization efficiency. In this paper, we propose a generative AI-empowered federated learning to address these challenges by leveraging the idea of FIlling the MIssing (FIMI) portion of local data. Specifically, FIMI can be considered as a resource-aware data augmentation method that effectively mitigates the data heterogeneity while ensuring efficient FL training. We first quantify the relationship between the training data amount and the learning performance. We then study the FIMI optimization problem with the objective of minimizing the device-side overall energy consumption subject to required learning performance constraints. The decomposition-based analysis and the cross-entropy searching method are leveraged to derive the solution, where each device is assigned suitable AI-synthesized data and resource utilization policy. Experiment results demonstrate that FIMI can save up to 50% of the device-side energy to achieve the target global test accuracy in comparison with the existing methods. Meanwhile, FIMI can significantly enhance the converged global accuracy under the non-independently-and-identically distribution (non-IID) data.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 21 Oct 2023.

Builds on

32 of 53 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  8. 2018Federated Learning with Non-IID Datacited by 1,108
  9. 2020Federated Learning with Matched Averagingcited by 564
  10. 2020Dataset Condensation with Gradient Matchingcited by 516
  11. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 327
  12. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
20 more
  1. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  2. 2023Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Servicescited by 76
  3. 2022Split Learning over Wireless Networks: Parallel Design and Resource Managementcited by 75
  4. 2020HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learningcited by 74
  5. 2020Wireless Communications for Collaborative Federated Learningcited by 47
  6. 2020Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networkscited by 42
  7. 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
  8. 2021AI-Native Network Slicing for 6G Networkscited by 31
  9. 2023Exploring Collaborative Distributed Diffusion-Based AI-Generated Content (AIGC) in Wireless Networkscited by 26
  10. 2023Federated Learning-Empowered AI-Generated Content in Wireless Networkscited by 26
  11. 2023Toward Understanding Generative Data Augmentationcited by 25
  12. 2015Distributed Optimization with Arbitrary Local Solverscited by 23
  13. 2022Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networkingcited by 18
  14. 2023Generative AI for Integrated Sensing and Communication: Insights from the Physical Layer Perspectivecited by 17
  15. 2019Machine Intelligence at the Edge with Learning Centric Power Allocationcited by 14
  16. 2023AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devicescited by 10
  17. 2023Joint Foundation Model Caching and Inference of Generative AI Services for Edge Intelligencecited by 9
  18. 2023Towards Fast Personalized Semi-Supervised Federated Learning in Edge Networks: Algorithm Design and Theoretical Guaranteecited by 5
  19. 2019Multi-hop Federated Private Data Augmentation with Sample Compressioncited by 4
  20. 2021Nothing Wasted: Full Contribution Enforcement in Federated Edge Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 5; 2026: 3.

13 papers.

Sort:

  1. 2024Hybrid RAG-empowered Multi-modal LLM for Secure Data Management in Internet of Medical Things: A Diffusion-based Contract Approachcited by 7
  2. 2024Blockchain-based Pseudonym Management for Vehicle Twin Migrations in Vehicular Edge Metaversecited by 4
  3. 2024Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Datacited by 4
  4. 2024IMFL-AIGC: Incentive Mechanism Design for Federated Learning Empowered by Artificial Intelligence Generated Contentcited by 3
  5. 2025Generative Artificial Intelligence for Internet of Things Computing: A Systematic Surveycited by 3
  6. 2025Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practicecited by 3
  7. 2026Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMscited by 1
  8. 2024Spatial-Temporal Generative AI for Traffic Flow Estimation with Sparse Data of Connected Vehiclescited by 0
  9. 2025Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approachcited by 0
  10. 2025AIGC-assisted Federated Learning for Edge Intelligence: Architecture Design, Research Challenges and Future Directionscited by 0
  11. 2025Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Designcited by 0
  12. 2026Cooperate to Compete: Strategic Data Generation and Incentivization Framework for Coopetitive Cross-Silo Federated Learningcited by 0
1 more
  1. 2026WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learningcited by 0