PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) with non-IID data often degrades client performance below local training baselines. Partial FL addresses this by federating only early layers that learn transferable features, but existing methods rely on ad-hoc, architecture-specific heuristics. We first conduct a systematic analysis of layer-wise generalization dynamics in FL, revealing an early-emerging transition between generalizable (safe-to-federate) and task-specific (should-remain-local) layers. Building on this, we introduce Principled Layer-wise Federated Learning (PLayer-FL), which aims to deliver the benefits of federation more robustly. PLayer-FL computes a novel federation-sensitivity metric efficiently after a single training epoch to choose the optimal split point for a given task. Inspired by model pruning, the metric quantifies each layer's robustness to aggregation and highlights where federation shifts from beneficial to detrimental. We show that this metric correlates strongly with established generalization measures across diverse architectures. Crucially, experiments demonstrate that PLayer-FL achieves consistently competitive performance across a wide range of tasks while distributing gains more equitably and reducing client-side regressions relative to baselines.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 50 references that are in the map. First posted on arXiv 12 Feb 2025.
Builds on
39 of 50 references.
References · 39
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
- 2019Similarity of Neural Network Representations Revisitedcited by 1,755
- 2018Federated Learning with Non-IID Datacited by 1,108
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
- 2017Federated Multi-Task Learningcited by 672
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
27 more
- 2018Rethinking the Value of Network Pruningcited by 599
- 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
- 2019Importance Estimation for Neural Network Pruningcited by 541
- 2019Federated Learning with Personalization Layerscited by 541
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
- 2019Fantastic Generalization Measures and Where to Find Themcited by 513
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 359
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
- 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
- 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 221
- 2015Convergent Learning: Do different neural networks learn the same representations?cited by 220
- 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
- 2020Salvaging Federated Learning by Local Adaptationcited by 142
- 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
- 2021Generalized Shape Metrics on Neural Representationscited by 112
- 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
- 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
- 2016Understanding Deep Convolutional Networkscited by 76
- 2018Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representationcited by 62
- 2021The Federated Tumor Segmentation (FeTS) Challengecited by 50
- 2022Cross-Silo Federated Learning: Challenges and Opportunitiescited by 38
- 2021Layer-wise Adaptive Model Aggregation for Scalable Federated Learningcited by 36
- 2023Towards Personalized Federated Learning via Heterogeneous Model Reassemblycited by 31
- 2021Layer-wise Model Pruning based on Mutual Informationcited by 19
- 2021New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learningcited by 11
- 2023FedLP: Layer-wise Pruning Mechanism for Communication-Computation Efficient Federated Learningcited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.