paper-with-me

홈 › Papers

Personalized Federated Learning via Convex Clustering

2022-02-01 · Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

We propose a parametric family of algorithms for personalized federated learning with locally convex user costs. The proposed framework is based on a generalization of convex clustering in which the differences between different users' models are penalized via a sum-of-norms penalty, weighted by a penalty parameter $\lambda$. The proposed approach enables "automatic" model clustering, without prior knowledge of the hidden cluster structure, nor the number of clusters. Analytical bounds on the weight parameter, that lead to simultaneous personalization, generalization and automatic model clustering are provided. The solution to the formulated problem enables personalization, by providing different models across different clusters, and generalization, by providing models different than the per-user models computed in isolation. We then provide an efficient algorithm based on the Parallel Direction Method of Multipliers (PDMM) to solve the proposed formulation in a federated server-users setting. Numerical experiments corroborate our findings. As an interesting byproduct, our results provide several generalizations to convex clustering.

📄 PDF Abstract BibTeX arXiv:2202.00718

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringFederated LearningPersonalized Federated Learning

Similar Papers 제목 키워드 기반

Personalized Multi-tier Federated Learning

2024-07-19 · Sourasekhar Banerjee, Ali Dadras, Alp Yurtsever, Monowar Bhuyan

The key challenge of personalized federated learning (PerFL) is to capture the statistical heterogeneity properties of data with inexpensive communications and gain customized performance for participating devices. To ad…

Federated LearningPersonalized Federated Learning

Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model Adaptation

2022-08-19 · Sichun Luo, Yuanzhang Xiao, Linqi Song

Federated recommendation applies federated learning techniques in recommendation systems to help protect user privacy by exchanging models instead of raw user data between user devices and the central server. Due to the …

AttributeClusteringFederated LearningGraph Neural Network+2

Personalized Cross-Silo Federated Learning on Non-IID Data

2020-07-07 · Yutao Huang, Lingyang Chu, Zirui Zhou, Lanjun Wang 외

Non-IID data present a tough challenge for federated learning. In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. We propose FedAMP, a new method employing f…

Federated Learning

Adaptive Personalized Federated Learning

2020-03-30 · Yuyang Deng, Mohammad Mahdi Kamani, Mehrdad Mahdavi

Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this pap…

Bilevel OptimizationFederated LearningPersonalized Federated Learning

Personalized Federated Learning with Clustering: Non-IID Heart Rate Variability Data Application

2021-08-04 · Joo Hun Yoo, Ha Min Son, Hyejun Jeong, Eun-Hye Jang 외

While machine learning techniques are being applied to various fields for their exceptional ability to find complex relations in large datasets, the strengthening of regulations on data ownership and privacy is causing i…

ClusteringFederated LearningHeart Rate VariabilityPersonalized Federated Learning+1