paper-with-me

Papers

Multi-Model Federated Learning with Provable Guarantees

2022-07-09 · Neelkamal Bhuyan, Sharayu Moharir, Gauri Joshi

Federated Learning (FL) is a variant of distributed learning where edge devices collaborate to learn a model without sharing their data with the central server or each other. We refer to the process of training multiple independent models simultaneously in a federated setting using a common pool of clients as multi-model FL. In this work, we propose two variants of the popular FedAvg algorithm for multi-model FL, with provable convergence guarantees. We further show that for the same amount of computation, multi-model FL can have better performance than training each model separately. We supplement our theoretical results with experiments in strongly convex, convex, and non-convex settings.

📄 PDF Abstract BibTeX arXiv:2207.04330

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningmodel

Similar Papers 제목 키워드 기반

Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning

2025-03-27 · Karlo Palenzuela, Ali Dadras, Alp Yurtsever, Tommy Löfstedt

Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, have been lacking in general non-smooth co…

Federated Learning

First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions

2025-12-25 · Egor Shulgin, Grigory Malinovsky, Sarit Khirirat, Peter Richtárik arxiv

Federated Learning (FL) enables collaborative training on decentralized data. Differential privacy (DP) is crucial for FL, but current private methods often rely on unrealistic assumptions (e.g., bounded gradients or het…

Federated Learning

Scalable Robust Federated Learning with Provable Security Guarantees

2021-09-29 · Andrew Liu, Jacky Y. Zhang, Nishant Kumar, Dakshita Khurana 외

Federated averaging, the most popular aggregation approach in federated learning, is known to be vulnerable to failures and adversarial updates from clients that wish to disrupt training. While median aggregation remains…

Federated Learning

Sustainable Federated Learning

2021-02-22 · Basak Guler, Aylin Yener

Potential environmental impact of machine learning by large-scale wireless networks is a major challenge for the sustainability of future smart ecosystems. In this paper, we introduce sustainable machine learning in fede…

BIG-bench Machine LearningFederated Learning

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

2022-11-21 · Yann Fraboni, Martin Van Waerebeke, Kevin Scaman, Richard Vidal 외

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending …

Machine Unlearning