اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدQuantized Federated Learning under Transmission Delay and Outage Constraints
107
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Federated learning (FL) has been recognized as a viable distributed learning paradigm which trains a machine learning model collaboratively with massive mobile devices in the wireless edge while protecting user privacy. Although various communication schemes have been proposed to expedite the FL process, most of them have assumed ideal wireless channels which provide reliable and lossless communication links between the server and mobile clients. Unfortunately, in practical systems with limited radio resources such as constraint on the training latency and constraints on the transmission power and bandwidth, transmission of a large number of model parameters inevitably suffers from quantization errors (QE) and transmission outage (TO). In this paper, we consider such non-ideal wireless channels, and carry out the first analysis showing that the FL convergence can be severely jeopardized by TO and QE, but intriguingly can be alleviated if the clients have uniform outage probabilities. These insightful results motivate us to propose a robust FL scheme, named FedTOE, which performs joint allocation of wireless resources and quantization bits across the clients to minimize the QE while making the clients have the same TO probability. Extensive experimental results are presented to show the superior performance of FedTOE for a deep learning-based classification task with transmission latency constraints.
قيم البحث
اقرأ أيضاً
In this paper, we propose a multiple-input multipleoutput (MIMO) transmission strategy that is closer to the Shannon limit than the existing strategies. Different from most existing strategies which only consider uniformly distributed discrete input
signals, we present a unified framework to optimize the MIMO precoder and the discrete input signal distribution jointly. First, a general model of MIMO transmission under discrete input signals and its equivalent formulation are established. Next, in order to maximize the mutual information between the input and output signals, we provide an algorithm that jointly optimizes the precoder and the input distribution. Finally, we compare our strategy with other existing strategies in the simulation. Numerical results indicate that our strategy narrows the gap between the mutual information and Shannon limit, and shows a lower frame error rate in simulation.
Source-channel coding for an energy limited wireless sensor node is investigated. The sensor node observes independent Gaussian source samples with variances changing over time slots and transmits to a destination over a flat fading channel. The fadi
ng is constant during each time slot. The compressed samples are stored in a finite size data buffer and need to be delivered in at most $d$ time slots. The objective is to design optimal transmission policies, namely, optimal power and distortion allocation, over the time slots such that the average distortion at destination is minimized. In particular, optimal transmission policies with various energy constraints are studied. First, a battery operated system in which sensor node has a finite amount of energy at the beginning of transmission is investigated. Then, the impact of energy harvesting, energy cost of processing and sampling are considered. For each energy constraint, a convex optimization problem is formulated, and the properties of optimal transmission policies are identified. For the strict delay case, $d=1$, $2D$ waterfilling interpretation is provided. Numerical results are presented to illustrate the structure of the optimal transmission policy, to analyze the effect of delay constraints, data buffer size, energy harvesting, processing and sampling costs.
In this paper, we study the trajectory design for a cellular-connected unmanned aerial vehicle (UAV) with given initial and final locations, while communicating with the ground base stations (GBSs) along its flight. We consider delay-limited communic
ations between the UAV and its associated GBSs, where a given signal-to-noise ratio (SNR) target needs to be satisfied at the receiver. However, in practice, due to various factors such as quality-of-service (QoS) requirement, GBSs availability and UAV mobility constraints, the SNR target may not be met at certain time periods during the flight, each termed as an outage duration. In this paper, we aim to optimize the UAV trajectory to minimize its mission completion time, subject to a constraint on the maximum tolerable outage duration in its flight. To tackle this non-convex problem, we first transform it into a more tractable form and thereby reveal some useful properties of the optimal trajectory solution. Based on these properties, we then further simplify the problem and propose efficient algorithms to check the feasibility of the problem as well as to obtain its optimal and high-quality suboptimal solutions, by leveraging graph theory and convex optimization techniques. Numerical results show that our proposed trajectory designs outperform the conventional method based on dynamic programming, in terms of both performance and complexity.
Edge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its
data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this work, we explore the new direction of energy-efficient radio resource management (RRM) for FEEL. To reduce devices energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling. They adapt to devices channel states and computation capacities so as to reduce their sum energy consumption while warranting learning performance. In contrast with the traditional rate-maximization designs, the derived optimal policies allocate more bandwidth to those scheduled devices with weaker channels or poorer computation capacities, which are the bottlenecks of synchronized model updates in FEEL. On the other hand, the scheduling priority function derived in closed form gives preferences to devices with better channels and computation capacities. Substantial energy reduction contributed by the proposed strategies is demonstrated in learning experiments.
By exploiting the computing power and local data of distributed clients, federated learning (FL) features ubiquitous properties such as reduction of communication overhead and preserving data privacy. In each communication round of FL, the clients up
date local models based on their own data and upload their local updates via wireless channels. However, latency caused by hundreds to thousands of communication rounds remains a bottleneck in FL. To minimize the training latency, this work provides a multi-armed bandit-based framework for online client scheduling (CS) in FL without knowing wireless channel state information and statistical characteristics of clients. Firstly, we propose a CS algorithm based on the upper confidence bound policy (CS-UCB) for ideal scenarios where local datasets of clients are independent and identically distributed (i.i.d.) and balanced. An upper bound of the expected performance regret of the proposed CS-UCB algorithm is provided, which indicates that the regret grows logarithmically over communication rounds. Then, to address non-ideal scenarios with non-i.i.d. and unbalanced properties of local datasets and varying availability of clients, we further propose a CS algorithm based on the UCB policy and virtual queue technique (CS-UCB-Q). An upper bound is also derived, which shows that the expected performance regret of the proposed CS-UCB-Q algorithm can have a sub-linear growth over communication rounds under certain conditions. Besides, the convergence performance of FL training is also analyzed. Finally, simulation results validate the efficiency of the proposed algorithms.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
