mlsanityData to 7 Oct 2026

Personalized Federated Learning under Model Dissimilarity Constraints

arXiv 2505.07575 ↗First posted 12 May 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

One of the defining challenges in federated learning is that of statistical heterogeneity among clients. We address this problem with KARULA, a regularized strategy for personalized federated learning, which constrains the pairwise model dissimilarities between clients based on the difference in their distributions, as measured by a surrogate for the 1-Wasserstein distance adapted for the federated setting. This allows the strategy to adapt to highly complex interrelations between clients, that e.g., clustered approaches fail to capture. We propose an inexact projected stochastic gradient algorithm to solve the constrained problem that the strategy defines, and show theoretically that it converges with smooth, possibly non-convex losses to a neighborhood of a stationary point with rate O(1/K). We demonstrate the effectiveness of KARULA on synthetic and real federated data sets.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 42 references that are in the map. First posted on arXiv 12 May 2025.

Builds on

23 of 42 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Learning with Non-IID Datacited by 1,099
  3. 2018LEAF: A Benchmark for Federated Settingscited by 780
  4. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  5. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  6. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  7. 2019Federated Learning with Personalization Layerscited by 533
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  9. 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 401
  10. 2020Adaptive Personalized Federated Learningcited by 353
  11. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 121
  12. 2022FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learningcited by 62
11 more
  1. 2020Wasserstein Embedding for Graph Learningcited by 56
  2. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  3. 2021Deep Federated Learning for Autonomous Drivingcited by 54
  4. 2019A Principled Approach for Learning Task Similarity in Multitask Learningcited by 32
  5. 2021A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularizationcited by 27
  6. 2022Wasserstein Task Embedding for Measuring Task Similaritiescited by 24
  7. 2020Two-sample Test using Projected Wasserstein Distancecited by 17
  8. 2022Personalized Federated Learning via Convex Clusteringcited by 10
  9. 2023Federated Wasserstein Distancecited by 8
  10. 2024CoBo: Collaborative Learning via Bilevel Optimizationcited by 5
  11. 2024A Universal Metric of Dataset Similarity for Cross-silo Federated Learningcited by 4

Built on by

Not cited yet.