Group Personalized Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) can help promote data privacy by training a shared model in a de-centralized manner on the physical devices of clients. In the presence of highly heterogeneous distributions of local data, personalized FL strategy seeks to mitigate the potential client drift. In this paper, we present the group personalization approach for applications of FL in which there exist inherent partitions among clients that are significantly distinct. In our method, the global FL model is fine-tuned through another FL training process over each homogeneous group of clients, after which each group-specific FL model is further adapted and personalized for any client. The proposed method can be well interpreted from a Bayesian hierarchical modeling perspective. With experiments on two real-world datasets, we demonstrate this approach can achieve superior personalization performance than other FL counterparts.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 4 Oct 2022.
Builds on
26 of 33 references.
References · 26
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Pointer Sentinel Mixture Modelscited by 3,096
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
- 2020Adaptive Federated Optimizationcited by 1,046
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2018Federated Learning for Mobile Keyboard Predictioncited by 572
- 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
- 2021Towards Personalized Federated Learningcited by 464
- 2020Adaptive Personalized Federated Learningcited by 358
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
14 more
- 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
- 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
- 2015Character-Aware Neural Language Modelscited by 132
- 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 118
- 2020Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognitioncited by 113
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
- 2018Federated Learning for Keyword Spottingcited by 95
- 2018Learning Private Neural Language Modeling with Attentive Aggregationcited by 49
- 2020FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measurecited by 46
- 2020Training Speech Recognition Models with Federated Learning: A Quality/Cost Frameworkcited by 46
- 2021Federated Acoustic Modeling For Automatic Speech Recognitioncited by 20
- 2020Enhancing Privacy via Hierarchical Federated Learningcited by 10
- 2019Federated Learning for Healthcare Informaticscited by 6
Built on by
Citing papers per year: 2024: 1.
1 paper.