mlsanityData to 14 Oct 2026

Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysis

arXiv 2504.06235 ↗First posted 8 Apr 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Much of federated learning (FL) focuses on settings where local dataset statistics remain the same between training and testing. However, this assumption often does not hold in practice due to distribution shifts, motivating the development of domain generalization (DG) approaches that leverage source domain data to train models capable of generalizing to unseen target domains. In this paper, we are motivated by two major gaps in existing work on FL and DG: (1) the lack of formal mathematical analysis of DG objectives; and (2) DG research in FL being limited to the star-topology architecture. We develop Decentralized Federated Domain Generalization with Style Sharing (textitStyleDDG), a decentralized DG algorithm which allows devices in a peer-to-peer network to achieve DG based on sharing style information inferred from their datasets. Additionally, we provide the first systematic approach to analyzing style-based DG training in decentralized networks. We cast existing centralized DG algorithms within our framework, and employ their formalisms to model textitStyleDDG. We then obtain analytical conditions under which convergence of textitStyleDDG can be guaranteed. Through experiments on popular DG datasets, we demonstrate that textitStyleDDG can obtain significant improvements in accuracy across target domains with minimal communication overhead compared to baseline decentralized gradient methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

36 of 56 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  9. 2021Domain Generalization: A Surveycited by 764
  10. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  11. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  12. 2021Domain Generalization with MixStylecited by 566
24 more
  1. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  2. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  3. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 367
  4. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  5. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  6. 2020Domain Adaptive Ensemble Learningcited by 156
  7. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  8. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 125
  9. 2017Network Topology and Communication-Computation Tradeoffs in Decentralized Optimizationcited by 122
  10. 2023Decentralized Federated Learning: A Survey and Perspectivecited by 86
  11. 2020An improved convergence analysis for decentralized online stochastic non-convex optimizationcited by 53
  12. 2021Federated Learning with Domain Generalizationcited by 41
  13. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  14. 2023Federated Domain Generalization: A Surveycited by 25
  15. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  16. 2023Benchmarking Algorithms for Federated Domain Generalizationcited by 14
  17. 2023Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networkscited by 13
  18. 2022NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Datacited by 12
  19. 2023Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalizationcited by 11
  20. 2024Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guaranteescited by 10
  21. 2023Multi-Source to Multi-Target Decentralized Federated Domain Adaptationcited by 6
  22. 2024Key Focus Areas and Enabling Technologies for 6Gcited by 6
  23. 2023Taming Subnet-Drift in D2D-Enabled Fog Learning: A Hierarchical Gradient Tracking Approachcited by 5
  24. 2024Overlay-based Decentralized Federated Learning in Bandwidth-limited Networkscited by 2

Built on by

Not cited yet.