mlsanityData to 7 Oct 2026

Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup

arXiv 2006.09801 ↗First posted 17 Jun 2020cs.LG stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inversely mixed up across different devices at the server. Numerical evaluations show that Mix2FLD achieves up to 16.7% higher test accuracy while reducing convergence time by up to 18.8% under asymmetric uplink-downlink channels compared to FL.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 11; 2023: 6; 2024: 4; 2025: 4.

29 papers.

Sort:

  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  2. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  3. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  4. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  5. 2022Federated Learning with GAN-based Data Synthesis for Non-IID Clientscited by 25
  6. 2023Green Edge AI: A Contemporary Surveycited by 24
  7. 2022DYNAFED: Tackling Client Data Heterogeneity with Global Dynamicscited by 22
  8. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  9. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  10. 2021Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Spacecited by 17
  11. 2024Federated Distillation: A Surveycited by 14
  12. 2023Feature Matching Data Synthesis for Non-IID Federated Learningcited by 13
17 more
  1. 2022Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestrationcited by 12
  2. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  3. 2022Communication-Efficient Federated Distillation with Active Data Samplingcited by 10
  4. 2022FedDKD: Federated Learning with Decentralized Knowledge Distillationcited by 9
  5. 2024Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutionscited by 8
  6. 2022Federated Distillation based Indoor Localization for IoT Networkscited by 6
  7. 2025Subgraph Federated Learning for Local Generalizationcited by 6
  8. 2023Knowledge Distillation in Federated Edge Learning: A Surveycited by 5
  9. 2022Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networkscited by 4
  10. 2022StatMix: Data augmentation method that relies on image statistics in federated learningcited by 4
  11. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  12. 2022Robust Federated Learning against both Data Heterogeneity and Poisoning Attack via Aggregation Optimizationcited by 3
  13. 2025Federated Learning-Distillation Alternation for Resource-Constrained IoTcited by 2
  14. 2022Fed-TDA: Federated Tabular Data Augmentation on Non-IID Datacited by 1
  15. 2023Heterogeneous Federated Learning Using Knowledge Codistillationcited by 0
  16. 2023Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Frameworkcited by 0
  17. 2025P2U: Progressive Precision Update For Efficient Model Distributioncited by 0