mlsanityData to 7 Oct 2026

Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings

arXiv 2603.02233 ↗First posted 13 Feb 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized Federated Learning (PFL) enables a collection of agents to collaboratively learn individual models without sharing raw data. We propose a new PFL approach in which each agent optimizes a weighted combination of all agents' empirical risks, with the weights learned from data rather than specified a priori. The novelty of our method lies in formulating the estimation of these collaborative weights as a kernel mean embedding estimation problem with multiple data sources, leveraging tools from multi-task averaging to capture statistical relationships between agents. This perspective yields a fully adaptive procedure that requires no prior knowledge of data heterogeneity and can automatically transition between global and local learning regimes. By recasting the objective as a high-dimensional mean estimation problem, we derive finite-sample guarantees on local excess risks for a broad class of distributions, explicitly quantifying the statistical gains of collaboration. To address communication constraints inherent to federated settings, we also propose a practical implementation based on random Fourier features, which allows one to trade communication cost for statistical efficiency. Numerical experiments validate our theoretical results.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

36 of 64 references.

References · 36

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2017A Survey on Multi-Task Learningcited by 838
  3. 2018LEAF: A Benchmark for Federated Settingscited by 780
  4. 2017Federated Multi-Task Learningcited by 669
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  6. 2020The Future of Digital Health with Federated Learningcited by 625
  7. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  8. 2019Federated Learning with Personalization Layerscited by 533
  9. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  10. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  11. 2021Towards Personalized Federated Learningcited by 462
  12. 2015An Introduction to Matrix Concentration Inequalitiescited by 391
24 more
  1. 2020Adaptive Personalized Federated Learningcited by 353
  2. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  3. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  4. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  5. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  6. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 154
  7. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  8. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  9. 2021Personalized Federated Learning with Gaussian Processescited by 76
  10. 2023Personalized Federated Learning under Mixture of Distributionscited by 37
  11. 2019Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphscited by 34
  12. 2022Adaptive and Robust Multi-Task Learningcited by 33
  13. 2021Satellite Based Computing Networks with Federated Learningcited by 25
  14. 2021On-Board Federated Learning for Dense LEO Constellationscited by 22
  15. 2022AsyncFLEO: Asynchronous Federated Learning for LEO Satellite Constellations with High-Altitude Platformscited by 18
  16. 2021Collaboration Equilibrium in Federated Learningcited by 15
  17. 2013Kernel Mean Estimation and Stein's Effectcited by 11
  18. 2023Personalized Online Federated Learning with Multiple Kernelscited by 11
  19. 2024CoBo: Collaborative Learning via Bilevel Optimizationcited by 5
  20. 2020High-Dimensional Multi-Task Averaging and Application to Kernel Mean Embeddingcited by 3
  21. 2024Estimation of multiple mean vectors in high dimensioncited by 3
  22. 2021Nonasymptotic one-and two-sample tests in high dimension with unknown covariance structurecited by 2
  23. 2023Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oraclescited by 2
  24. 2025Adaptive collaboration for online personalized distributed learning with heterogeneous clientscited by 2

Built on by

Not cited yet.