Age of information and unbiased federated learning in energy harvesting error-prone channels

Download

10495849.pdf

Date

2022-8-29

Author

Çakır, Zeynep

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

283
views

67
downloads

Federated learning is a communication-efficient and privacy-preserving learning tech nique for collaborative training of machine learning models on vast amounts of data produced and stored locally on the distributed users. In this thesis, unbiased feder ated learning methods that achieve a similar convergence as state-of-the-art federated learning methods in scenarios with various constraints like error-prone channel or in termittent energy availability are investigated. In addition, a prevalent metric called the age of information (AoI), which quantifies the staleness of the information at the destination, is studied under energy constraints and exploited to increase the perfor mance of federated learning algorithms. Firstly, a constrained Markov decision problem that aims to minimize the average age of information over an imperfect channel and under energy constraints is investigated. An optimal threshold-based scheduling policy is obtained and the optimal time aver age AoI and age violation probabilities are derived. Secondly, a federated learning algorithm that jointly designs the unbiased user scheduling and gradient weighting according to the energy and channel profile of each user is presented. It is shown that the proposed algorithm provides a high test accuracy and a convergence guarantees, which is close to the algorithms that have no energy or channel constraints. Lastly, the effect of AoI on federated learning with heterogeneous users and different datasets is studied, and the performance is demonstrated by experiments.

Subject Keywords

Federated learning, Energy harvesting, Age of information, Momentum, Wireless communications

URI

https://hdl.handle.net/11511/99607

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Activity Learning from Lifelogging Images Belli, Kader; Akbaş, Emre; Yazıcı, Adnan (2019-01-01) The analytics of lifelogging has generated great interest for data scientists because big and multi-dimensional data are generated as a result of lifelogging activities. In this paper, the NTCIR Lifelog dataset is used to learn activities from an image point of view. Minute definitions are classified into activity classes using images and annotations, which serve as a basis for various classification techniques, namely SVMs and convolutional neural network structures (CNN), for learning activities. The perf...
Competing labels: a heuristic approach to pseudo-labeling in deep semi-supervised learning Bayrak, Hamdi Burak; Ertekin Bolelli, Şeyda; Yücel, Hamdullah; Department of Scientific Computing (2022-2-10) Semi-supervised learning is one of the dominantly utilized approaches to reduce the reliance of deep learning models on large-scale labeled data. One mostly used method of this approach is pseudo-labeling. However, pseudo-labeling, especially its originally proposed form tends to remarkably suffer from noisy training when the assigned labels are false. In order to mitigate this problem, in our work, we investigate the gradient sent to the neural network and propose a heuristic method, called competing label...
Deep learning approach for laboratory mice grimace scaling Eral, Mustafa; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2016) Deep learning is extremely attractive research topic in pattern recognition and machine learning areas. Applications in speech recognition, natural language processing, and machine vision fields gained huge acceleration in performance by employing deep learning. In this thesis, deep learning is used for medical purposes in order to scale pain degree of drug stimulated mice by examining facial grimace. For this purpose each frame in the videos in the training set were scaled manually by experts according to ...
A deep learning approach for the transonic flow field predictions around airfoils Duru, Cihat; Alemdar, Hande; Baran, Özgür Uğraş (2022-01-01) Learning from data offers new opportunities for developing computational methods in research fields, such as fluid dynamics, which constantly accumulate a large amount of data. This study presents a deep learning approach for the transonic flow field predictions around airfoils. The physics of transonic flow is integrated into the neural network model by utilizing Reynolds-averaged Navier–Stokes (RANS) simulations. A detailed investigation on the performance of the model is made both qualitatively and quant...
Adapted Infinite Kernel Learning by Multi-Local Algorithm Akyuz, Sureyya Ozogur; Ustunkar, Gurkan; Weber, Gerhard Wilhelm (2016-05-01) The interplay of machine learning (ML) and optimization methods is an emerging field of artificial intelligence. Both ML and optimization are concerned with modeling of systems related to real-world problems. Parameter selection for classification models is an important task for ML algorithms. In statistical learning theory, cross-validation (CV) which is the most well-known model selection method can be very time consuming for large data sets. One of the recent model selection techniques developed for supp...

Citation Formats

Z. Çakır, “Age of information and unbiased federated learning in energy harvesting error-prone channels,” M.S. - Master of Science, Middle East Technical University, 2022.