mlsanityData to 7 Oct 2026

On the Generalization of Wasserstein Robust Federated Learning

arXiv 2206.01432 ↗First posted 3 Jun 2022cs.LG cs.DCcited by 9

Not on the map. Why?

Abstract (arXiv)

In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust optimization scheme called WAFL. Leveraging its duality, we frame WAFL as an empirical surrogate risk minimization problem, and solve it using a local SGD-based algorithm with convergence guarantees. We show that the robustness of WAFL is more general than related approaches, and the generalization bound is robust to all adversarial distributions inside the Wasserstein ball (ambiguity set). Since the center location and radius of the Wasserstein ball can be suitably modified, WAFL shows its applicability not only in robustness but also in domain adaptation. Through empirical evaluation, we demonstrate that WAFL generalizes better than the vanilla FedAvg in non-i.i.d. settings, and is more robust than other related methods in distribution shift settings. Further, using benchmark datasets we show that WAFL is capable of generalizing to unseen target domains.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 3 Jun 2022.

Builds on

36 of 50 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  9. 2018Federated Learning with Non-IID Datacited by 1,099
  10. 2016Adversarial Machine Learning at Scalecited by 934
  11. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
24 more
  1. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  2. 2017Federated Multi-Task Learningcited by 669
  3. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  4. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  5. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  6. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  7. 2019Agnostic Federated Learningcited by 451
  8. 2020Adaptive Personalized Federated Learningcited by 353
  9. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  10. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  11. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  12. 2021A Field Guide to Federated Optimizationcited by 312
  13. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
  14. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  15. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 182
  16. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
  17. 2020Geometric Dataset Distances via Optimal Transportcited by 157
  18. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  19. 2015Distributionally Robust Logistic Regressioncited by 124
  20. 2021Distributionally Robust Federated Averagingcited by 104
  21. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  22. 2020Fairness-aware Agnostic Federated Learningcited by 87
  23. 2020A Theory of Multiple-Source Adaptation with Limited Target Labeled Datacited by 18
  24. 2022Wasserstein Distributionally Robust Optimization with Wasserstein Barycenterscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 4; 2026: 2.

9 papers.

  1. 2023Federated Domain Generalization: A Surveycited by 25
  2. 2022Label driven Knowledge Distillation for Federated Learning with non-IID Datacited by 3
  3. 2024Distributionally Robust Clustered Federated Learning: A Case Study in Healthcarecited by 2
  4. 2025Convergence of Agnostic Federated Averagingcited by 2
  5. 2025Distributionally Robust Federated Learning with Outlier Resiliencecited by 1
  6. 2025Distributionally Robust Federated Learning: An ADMM Algorithmcited by 0
  7. 2025Data Valuation and Selection in a Federated Model Marketplacecited by 0
  8. 2026Distributionally Robust Federated Learning with Multi-Source Datacited by 0
  9. 2026FedeRage: Provably Convergent Agnostic Federated Learning under General Client Driftcited by 0