paper-with-me

홈 › Papers

Federated Asymptotics: a model to compare federated learning algorithms

2021-08-16 · Gary Cheng, Karan Chadha, John Duchi

We propose an asymptotic framework to analyze the performance of (personalized) federated learning algorithms. In this new framework, we formulate federated learning as a multi-criterion objective, where the goal is to minimize each client's loss using information from all of the clients. We analyze a linear regression model where, for a given client, we may theoretically compare the performance of various algorithms in the high-dimensional asymptotic limit. This asymptotic multi-criterion approach naturally models the high-dimensional, many-device nature of federated learning. These tools make fairly precise predictions about the benefits of personalization and information sharing in federated scenarios -- at least in our (stylized) model -- including that Federated Averaging with simple client fine-tuning achieves the same asymptotic risk as the more intricate meta-learning and proximal-regularized approaches and outperforming Federated Averaging without personalization. We evaluate these predictions on federated versions of the EMNIST, CIFAR-100, Shakespeare, and Stack Overflow datasets, where the experiments corroborate the theoretical predictions, suggesting such frameworks may provide a useful guide to practical algorithmic development.

📄 PDF Abstract BibTeX arXiv:2108.07313

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningMeta-LearningPersonalized Federated Learning

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Federated Learning on Riemannian Manifolds

2022-06-12 · Jiaxiang Li, Shiqian Ma

Federated learning (FL) has found many important applications in smart-phone-APP based machine learning applications. Although many algorithms have been studied for FL, to the best of our knowledge, algorithms for FL wit…

Federated Learning

A Benchmark for Federated Hetero-Task Learning

2022-06-07 · Liuyi Yao, Dawei Gao, Zhen Wang, Yuexiang Xie 외

To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants i…

Federated LearningMeta-LearningMulti-Task LearningText Generation

Federated Learning via Inexact ADMM

2022-04-22 · Shenglong Zhou, Geoffrey Ye Li

One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different …

Federated Learning

Federated Learning of N-gram Language Models

2019-10-08 · CONLL 2019 11 · Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews, Adeline Wong 외

We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to train global models for portable devices suc…

Federated LearningLanguage Modelling

Federated Learning Algorithms for Generalized Mixed-effects Model (GLMM) on Horizontally Partitioned Data from Distributed Sources

2021-09-28 · Wentao Li, Jiayi Tong, Md. Monowar Anjum, Noman Mohammed 외

Objectives: This paper develops two algorithms to achieve federated generalized linear mixed effect models (GLMM), and compares the developed model's outcomes with each other, as well as that from the standard R package …

Federated Learning