mlsanityData to 14 Oct 2026

FedAli: Personalized Federated Learning Alignment with Prototype Layers for Generalized Mobile Services

arXiv 2411.10595 ↗First posted 15 Nov 2024cs.LG cs.CR cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Personalized Federated Learning (PFL) enables distributed training on edge devices, allowing models to collaboratively learn global patterns while tailoring their parameters to better fit each client's local data, all while preserving data privacy. However, PFL faces two key challenges in mobile systems: client drift, where heterogeneous data cause model divergence, and the overlooked need for client generalization, as the dynamic of mobile sensing demands adaptation beyond local environments. To overcome these limitations, we introduce Federated Alignment (FedAli), a prototype-based regularization technique that enhances inter-client alignment while strengthening the robustness of personalized adaptations. At its core, FedAli introduces the ALignment with Prototypes (ALP) layer, inspired by human memory, to enhance generalization by guiding inference embeddings toward personalized prototypes while reducing client drift through alignment with shared prototypes during training. By leveraging an optimal transport plan to compute prototype-embedding assignments, our approach allows pre-training the prototypes without any class labels to further accelerate convergence and improve performance. Our extensive experiments show that FedAli significantly enhances client generalization while preserving strong personalization in heterogeneous settings.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 61 references that are in the map. First posted on arXiv 15 Nov 2024.

Builds on

37 of 61 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  10. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  11. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  12. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
25 more
  1. 2021Model-Contrastive Federated Learningcited by 766
  2. 2016Language Modeling with Gated Convolutional Networkscited by 702
  3. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  4. 2019Federated Learning with Personalization Layerscited by 541
  5. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  6. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  7. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  8. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  9. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  10. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  11. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  12. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  13. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  14. 2022Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learningcited by 71
  15. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 67
  16. 2021Personalized Federated Learning through Local Memorizationcited by 57
  17. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  18. 2018Protecting Sensory Data against Sensitive Inferencescited by 45
  19. 2022FedTP: Federated Learning by Transformer Personalizationcited by 36
  20. 2022Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognitioncited by 29
  21. 2022FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learningcited by 27
  22. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
  23. 2022Federated Few-Shot Learning for Mobile NLPcited by 15
  24. 2022The Future of Consumer Edge-AI Computingcited by 12
  25. 2024Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FedRD: Reducing Divergences for Generalized Federated Learning via Heterogeneity-aware Parameter Guidancecited by 0
  2. 2026FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivitycited by 0