mlsanityData to 7 Oct 2026

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

arXiv 2606.16655 ↗First posted 15 Jun 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions. In particular, the interaction of domain shift and label shift across clients induces misaligned feature representations that cannot be corrected through iterative optimization. Existing OSFL methods rely on distillation, server-side generation or ensemble-based aggregation, but assume aligned representations or address domain and label shift separately. We introduce SLOT-Align (Single-round, Learning-free Optimal Transport Alignment), a geometry-aware feature harmonization framework for OSFL. SLOT-Align uses a shared frozen encoder to extract compact feature statistics, constructs a global reference via Bures-Wasserstein barycenters, and aligns local representations using closed-form geodesic optimal transport maps. The method is computationally efficient and can be combined with existing OSFL pipelines relying on frozen encoders without modifying their training procedures. Extensive experiments across multiple benchmarks, pretrained backbones, and OSFL methods show that SLOT-Align consistently improves accuracy and robustness under joint domain and label shift.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

35 of 51 references.

References · 35

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  6. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  7. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  8. 2015Optimal Transport for Domain Adaptationcited by 457
  9. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  10. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  11. 2019Model Fusion via Optimal Transportcited by 217
  12. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
23 more
  1. 2019One-Shot Federated Learningcited by 124
  2. 2020Distilled One-Shot Federated Learningcited by 108
  3. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  4. 2020Practical One-Shot Federated Learning for Cross-Silo Settingcited by 76
  5. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 57
  6. 2022Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environmentscited by 49
  7. 2018Effects of Degradations on Deep Neural Network Architecturescited by 47
  8. 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillationcited by 45
  9. 2022Multi-Level Branched Regularization for Federated Learningcited by 34
  10. 2023Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Modelcited by 33
  11. 2024Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boostingcited by 27
  12. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  13. 2024FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Modelscited by 17
  14. 2024FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Modelscited by 16
  15. 2024Revisiting Ensembling in One-Shot Federated Learningcited by 13
  16. 2022An Optimal Transport Approach to Personalized Federated Learningcited by 12
  17. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  18. 2024One-shot Federated Learning via Synthetic Distiller-Distillate Communicationcited by 12
  19. 2024FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusioncited by 11
  20. 2025One-shot Federated Learning Methods: A Practical Guidecited by 6
  21. 2025Capture Global Feature Statistics for One-Shot Federated Learningcited by 6
  22. 2023One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Modelscited by 5
  23. 2025FedBEns: One-Shot Federated Learning based on Bayesian Ensemblecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model Analysiscited by 0