An Efficiency-Boosting Client Selection Scheme for Federated Learning With Fairness Guarantee
Reads0
Chats0
TLDR
An estimation of the model exchange time between each client and the server is proposed, based on which a fairness guaranteed algorithm termed RBCS-F for problem-solving is designed.Abstract:
The issue of potential privacy leakage during centralized AI’s model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with the privacy issue by allowing clients to perform model training locally, without the necessity to upload their personal sensitive data. In FL, the number of clients could be sufficiently large, but the bandwidth available for model distribution and re-upload is quite limited, making it sensible to only involve part of the volunteers to participate in the training process. The client selection policy is critical to an FL process in terms of training efficiency, the final model’s quality as well as fairness. In this article, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a $\mathbf {C^2MAB}$ C 2 MAB -based method is proposed for estimation of the model exchange time between each client and the server, based on which we design a fairness guaranteed algorithm termed RBCS-F for problem-solving. The regret of RBCS-F is strictly bounded by a finite constant, justifying its theoretical feasibility. Barring the theoretical results, more empirical data can be derived from our real training experiments on public datasets.read more
Citations
More filters
Posted Content
Stochastic Client Selection for Federated Learning with Volatile Clients.
TL;DR: This paper investigates the client selection problem under a volatile context, in which the local training of heterogeneous clients is likely to fail due to various kinds of reasons and in different levels of frequency.
Journal ArticleDOI
AUCTION: Automated and Quality-Aware Client Selection Framework for Efficient Federated Learning
TL;DR: AUCTION, an Automated and qUality-aware Client selecTION framework for efficient FL, which can evaluate the learning quality of clients and select them automatically with quality-awareness for a given FL task within a limited budget is proposed.
Journal ArticleDOI
Online Client Scheduling for Fast Federated Learning
TL;DR: This letter reformulates the client scheduling problem as a multi-armed bandit program and proposes an online scheduling scheme based on $\epsilon $ -greedy algorithm to achieve a tradeoff between exploration and exploitation.
Journal ArticleDOI
On Demand Fog Federations for Horizontal Federated Learning in IoV
TL;DR: A horizontal-based federated learning architecture, empowered by fog federations, devised for the mobile environment is proposed and results show that the proposed model can achieve better accuracy and quality of service than other models presented in the literature.
Proceedings ArticleDOI
Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization
TL;DR: It is shown through simulations that the communication time can be significantly decreased using the algorithm, compared to uniformly random participation, and an analytical solution to the minimization problem is found.
References
More filters
Posted Content
Communication-Efficient Learning of Deep Networks from Decentralized Data
TL;DR: This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.
Proceedings Article
Communication-Efficient Learning of Deep Networks from Decentralized Data
TL;DR: In this paper, the authors presented a decentralized approach for federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets.
Proceedings ArticleDOI
A contextual-bandit approach to personalized news article recommendation
TL;DR: This work model personalized recommendation of news articles as a contextual bandit problem, a principled approach in which a learning algorithm sequentially selects articles to serve users based on contextual information about the users and articles, while simultaneously adapting its article-selection strategy based on user-click feedback to maximize total user clicks.
Book
Stochastic Network Optimization with Application to Communication and Queueing Systems
TL;DR: In this article, the authors present a modern theory of analysis, control, and optimization for dynamic networks, including wireless networks with time-varying channels, mobility, and randomly arriving traffic.
Proceedings Article
Improved Algorithms for Linear Stochastic Bandits
TL;DR: A simple modification of Auer's UCB algorithm achieves with high probability constant regret and improves the regret bound by a logarithmic factor, though experiments show a vast improvement.
Related Papers (5)
Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
Takayuki Nishio,Ryo Yonetani +1 more