Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalization
Not on the map. Why?
Abstract (arXiv)
Federated learning is an efficient framework designed to facilitate collaborative model training across multiple distributed devices while preserving user data privacy. A significant challenge of federated learning is data-level heterogeneity, i.e., skewed or long-tailed distribution of private data. Although various methods have been proposed to address this challenge, most of them assume that the underlying global data is uniformly distributed across all clients. This paper investigates data-level heterogeneity federated learning with a brief review and redefines a more practical and challenging setting called Skewed Heterogeneous Federated Learning (SHFL). Accordingly, we propose a novel Federated Prototype Rectification with Personalization which consists of two parts: Federated Personalization and Federated Prototype Rectification. The former aims to construct balanced decision boundaries between dominant and minority classes based on private data, while the latter exploits both inter-class discrimination and intra-class consistency to rectify empirical prototypes. Experiments on three popular benchmarks show that the proposed approach outperforms current state-of-the-art methods and achieves balanced performance in both personalization and generalization.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 53 of its 96 references that are in the map. First posted on arXiv 15 Aug 2024.
Builds on
53 of 96 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2021Towards Personalized Federated Learningcited by 462
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
38 more
- 2021Deep Long-Tailed Learning: A Surveycited by 416
- 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
- 2020Adaptive Personalized Federated Learningcited by 353
- 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
- 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
- 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
- 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
- 2019Federated Evaluation of On-device Personalizationcited by 147
- 2020Federated Visual Classification with Real-World Data Distributioncited by 126
- 2020FedVision: An Online Visual Object Detection Platform Powered by Federated Learningcited by 121
- 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
- 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
- 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
- 2021Distributional Robustness Loss for Long-tail Learningcited by 84
- 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 67
- 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
- 2021Towards Fairness-Aware Federated Learningcited by 57
- 2020Federated learning with class imbalance reductioncited by 52
- 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
- 2020What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentationcited by 50
- 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 43
- 2018Multi-objective Evolutionary Federated Learningcited by 42
- 2022MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcarecited by 36
- 2022FedTP: Federated Learning by Transformer Personalizationcited by 36
- 2021Towards Model Agnostic Federated Learning Using Knowledge Distillationcited by 31
- 2022Learning to Re-weight Examples with Optimal Transport for Imbalanced Classificationcited by 23
- 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
- 2022CalFAT: Calibrated Federated Adversarial Training with Label Skewnesscited by 20
- 2022FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillationcited by 19
- 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
- 2022Clustered Vehicular Federated Learning: Process and Optimizationcited by 15
- 2023FedSampling: A Better Sampling Strategy for Federated Learningcited by 8
- 2022Towards Federated Long-Tailed Learningcited by 7
- 2023Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentationcited by 5
- 2021GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalizationcited by 4
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 2.
2 papers.