mlsanityData to 7 Oct 2026

Representation-Aligned Multi-Scale Personalization for Federated Learning

arXiv 2604.11278 ↗First posted 13 Apr 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In federated learning (FL), accommodating clients with diverse resource constraints remains a significant challenge. A widely adopted approach is to use a shared full-size model, from which each client extracts a submodel aligned with its computational budget. However, regardless of the specific scoring strategy, these methods rely on the same global backbone, limiting both structural diversity and representational adaptation across clients. This paper presents FRAMP, a unified framework for personalized and resource-adaptive federated learning. Instead of relying on a fixed global model, FRAMP generates client-specific models from compact client descriptors, enabling fine-grained adaptation to both data characteristics and computational budgets. Each client trains a tailored lightweight submodel and aligns its learned representation with others to maintain global semantic consistency. Extensive experiments on vision and graph benchmarks demonstrate that FRAMP enhances generalization and adaptivity across a wide range of client settings.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 66 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

46 of 66 references.

References · 46

  1. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  2. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  6. 2019Federated Learning with Personalization Layerscited by 533
  7. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  9. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  10. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  11. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  12. 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
34 more
  1. 2021Personalized Federated Learning using Hypernetworkscited by 210
  2. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  3. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  4. 2019Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterizationcited by 187
  5. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
  6. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 122
  7. 2020Learning the Pareto Front with Hypernetworkscited by 122
  8. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 122
  9. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  10. 2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
  11. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 95
  12. 2022Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learningcited by 81
  13. 2021Top-KAST: Top-K Always Sparse Trainingcited by 79
  14. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  15. 2019Hypernetwork functional image representationcited by 65
  16. 2020LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasetscited by 60
  17. 2021Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Bettercited by 54
  18. 2022Personalized Subgraph Federated Learningcited by 54
  19. 2021How Well Do Sparse Imagenet Models Transfer?cited by 50
  20. 2022FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clientscited by 46
  21. 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
  22. 2022Sparse Random Networks for Communication-Efficient Federated Learningcited by 32
  23. 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reductioncited by 24
  24. 2023PeFLL: Personalized Federated Learning by Learning to Learncited by 21
  25. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
  26. 2019Personalization of Deep Learningcited by 18
  27. 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneitycited by 13
  28. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  29. 2021Communication-Efficient and Personalized Federated Lottery Ticket Learningcited by 10
  30. 2021From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimizationcited by 8
  31. 2023NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clientscited by 7
  32. 2025HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmarkcited by 7
  33. 2025Subgraph Federated Learning for Local Generalizationcited by 6
  34. 2025Personalized Subgraph Federated Learning with Sheaf Collaborationcited by 1

Built on by

Not cited yet.