paper-with-me

홈 › Papers

Federated-EM with heterogeneity mitigation and variance reduction

2021-12-01 · NeurIPS 2021 12 · Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Geneviève Robin

The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models. As in any other field of machine learning, applications of latent variable models to very large datasets make the use of advanced parallel and distributed architecture mandatory. This paper introduces FedEM, which is the first extension of the EM algorithm to the federated learning context. FedEM is a new communication efficient method, which handles partial participation of local devices, and is robust to heterogeneous distribution of the datasets. To alleviate the communication bottleneck, FedEM compresses appropriately defined complete data sufficient statistics. We also develop and analyze an extension of FedEM to further incorporate a variance reduction scheme. In all cases, we derive finite-time complexity bounds for smooth non-convex problems. Numerical results are presented to support our theoretical findings, as well as an application to federated missing values imputation for biodiversity monitoring.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningImputationMissing Values

Similar Papers 제목 키워드 기반

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

2021-11-03 · Aymeric Dieuleveut, Gersende Fort, Eric Moulines, Geneviève Robin

The Expectation Maximization (EM) algorithm is the default algorithm for inference in latent variable models. As in any other field of machine learning, applications of latent variable models to very large datasets make …

Federated LearningImputationMissing Values

Differential Privacy Meets Federated Learning under Communication Constraints

2021-01-28 · Nima Mohammadi, Jianan Bai, Qiang Fan, Yifei Song 외

The performance of federated learning systems is bottlenecked by communication costs and training variance. The communication overhead problem is usually addressed by three communication-reduction techniques, namely, mod…

Federated LearningModel Compression

Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning

2026-05-17 · Vedant Waykole, Haroon R. Lone arxiv

Federated learning on edge devices must cope with non-IID client data and tight memory budgets. Adaptive optimizers like Adam stabilize training under data heterogeneity but require storing full-precision momentum and va…

Federated Learning

Sociodynamics-inspired Adaptive Coalition and Client Selection in Federated Learning

2025-06-03 · Alessandro Licciardi, Roberta Raineri, Anton Proskurnikov, Lamberto Rondoni 외

Federated Learning (FL) enables privacy-preserving collaborative model training, yet its practical strength is often undermined by client data heterogeneity, which severely degrades model performance. This paper proposes…

Federated LearningPrivacy Preserving

Towards Heterogeneous Quantum Federated Learning: Challenges and Solutions

2025-11-27 · Ratun Rahman, Dinh C. Nguyen, Christo Kurisummoottil Thomas, Walid Saad arxiv

Quantum federated learning (QFL) combines quantum computing and federated learning to enable decentralized model training while maintaining data privacy. QFL can improve computational efficiency and scalability by taking…

Computational EfficiencyFederated Learning