FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devices
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) on heterogeneous edge devices must jointly accommodate unequal resource budgets and domain-shifted local data. Existing resource-adaptive methods decide how much of a model each client trains but not where retained capacity should reside or how it should be shared, whereas federated domain-generalization methods usually assume a shared full architecture. Uniform compression can therefore discard high-utility channels, and a single aggregation path can mix transferable features with domain-sensitive updates. We propose FedSAP, a domain-aware heterogeneous FL framework that casts structured pruning as budget-constrained tri-state channel allocation. FedSAP converts each keep ratio into non-uniform layer budgets, assigns stable channels to a Global pool, useful domain-sensitive channels to pseudo-domain-specific Private pools, and low-utility channels to a Dropped state. This partition lets broadly useful features benefit from cross-client pooling while isolating domain-sensitive updates from incompatible clients. Domain-Guided Assignment infers pseudo-domains from shallow-gradient similarity, while Type-Matched Aggregation restricts each channel to its intended sharing scope. Across three random seeds, FedSAP reaches 76.00% and 72.67% mean global accuracy on Digits and Office-Caltech, exceeding the strongest baseline by 1.70 and 4.92 percentage points while supporting client pruning ratios of up to 80% across heterogeneous clients.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 1 Oct 2026.
Builds on
22 of 33 references.
References · 22
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2019Deep Leakage from Gradientscited by 1,004
- 2021Model-Contrastive Federated Learningcited by 762
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
- 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 219
- 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
- 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
- 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
- 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
- 2020Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learningcited by 37
10 more
- 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
- 2024FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneitycited by 13
- 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
- 2023NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clientscited by 7
- 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7
- 2025Federated Domain Generalization with Data-free On-server Matching Gradientcited by 7
- 2023Principled Federated Domain Adaptation: Gradient Projection and Auto-Weightingcited by 6
- 2024FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter Updatecited by 3
- 2026Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Packcited by 2
- 2026CA-HFP: Curvature-Aware Heterogeneous Federated Pruning with Model Reconstructioncited by 1
Built on by
Not cited yet.