mlsanityData to 7 Oct 2026

Addressing Heterogeneity in Federated Learning via Distributional Transformation

arXiv 2210.15025 ↗First posted 26 Oct 2022cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs from one client to another. Existing personalized FL algorithms are only applicable to narrow cases, e.g., one or two data classes per client, and therefore they do not satisfactorily address FL under varying levels of data heterogeneity. In this paper, we propose a novel framework, called DisTrans, to improve FL performance (i.e., model accuracy) via train and test-time distributional transformations along with a double-input-channel model structure. DisTrans works by optimizing distributional offsets and models for each FL client to shift their data distribution, and aggregates these offsets at the FL server to further improve performance in case of distributional heterogeneity. Our evaluation on multiple benchmark datasets shows that DisTrans outperforms state-of-the-art FL methods and data augmentation methods under various settings and different degrees of client distributional heterogeneity.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 40 of its 50 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

40 of 50 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  8. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  9. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  10. 2019Towards Federated Learning at Scale: System Designcited by 826
  11. 2021Model-Contrastive Federated Learningcited by 762
  12. 2020Personalized Federated Learning with Moreau Envelopescited by 612
28 more
  1. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  2. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  4. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  5. 2019Federated Machine Learning: Concept and Applicationscited by 409
  6. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  7. 2019Adversarial Examples Improve Image Recognitioncited by 283
  8. 2021Personalized Federated Learning using Hypernetworkscited by 210
  9. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
  10. 2019On the Convergence of Local Descent Methods in Federated Learningcited by 150
  11. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  12. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
  13. 2020Better Aggregation in Test-Time Augmentationcited by 121
  14. 2019Adversarial AutoAugmentcited by 111
  15. 2018Blockchained On-Device Federated Learningcited by 105
  16. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  17. 2021Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learningcited by 78
  18. 2020Shape-Texture Debiased Neural Network Trainingcited by 76
  19. 2019Accelerating Federated Learning via Momentum Gradient Descentcited by 75
  20. 2020Fast-Convergent Federated Learningcited by 61
  21. 2020Cost-Effective Federated Learning Designcited by 61
  22. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  23. 2020Learning Loss for Test-Time Augmentationcited by 56
  24. 2020Federated Learning with Only Positive Labelscited by 55
  25. 2017Smart Augmentation - Learning an Optimal Data Augmentation Strategycited by 54
  26. 2021Local Adaptivity in Federated Learning: Convergence and Consistencycited by 31
  27. 2021Enhancing Adversarial Robustness via Test-time Transformation Ensemblingcited by 27
  28. 2020Device Heterogeneity in Federated Learning: A Superquantile Approachcited by 20

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1; 2025: 1.

6 papers.

  1. 2023Multimodal Federated Learning in Healthcare: a Reviewcited by 13
  2. 2023Importance of Smoothness Induced by Optimizers in FL4ASR: Towards Understanding Federated Learning for End-to-End ASRcited by 8
  3. 2023Towards Instance-adaptive Inference for Federated Learningcited by 7
  4. 2023Fake It Till Make It: Federated Learning with Consensus-Oriented Generationcited by 6
  5. 2024Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Siloscited by 3
  6. 2025FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Freecited by 0