Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 45 for “"Client-Selection"”.
-
Adaptive client selection and upgrade of resources for robust federated learning
… FL. However, the limitations while selecting the clients and reducing the communication costs still threaten FL performance and its applicability in real scenarios. From these premises, this dissertation fills the lacking of the existing research outcomes. Particularly, the contributions of this …
-
Judgment and choice in client selection: An analysis of decision-making in the prospecting stage of the selling process
Based on the premise that research on sales performance should take a more micro-approach, this dissertation investigates salespeoples' decision processes during the prospecting stage of the sales process. More specifically, the dissertation addresses potential differences in decision processes …
-
Relaxing Core Assumptions: the Impact of Data, Model and Participation Heterogeneity on Performance, Privacy and Fairness in Federated Learning
… privacy by design. An FL design consists of clients training models on private data and a central server aggregating a global model based on the consensus among clients. In an ideal scenario, the training data and computing resources are identically and independently distributed (i.i.d.) …
-
Advanced decentralized techniques for privacy-preserving continuous authentication and resource efficiency
… while addressing resource optimization and client selection challenges in decentralized systems. By tackling issues such as resource efficiency, scalability, and secure client participation, this research enhances the practicality and performance of decentralized authentication mechanisms in …
-
Fairness in Continual Federated Learning
… machine learning technique that enables multiple clients to collaboratively train a shared model without sharing their data, while also adapting to new classes without forgetting previously learned ones. Currently, there are limited evaluation models and metrics for measuring fairness in CFL, and …
-
Enhancing Reliability and Efficiency in IoT Networks: A Study on UAV-Aided Mobile Edge Computing, Fault-Tolerant Federated Reinforcement Learning, and Energy-Efficient Knowledge Distillation on the Internet of Drones
… Offloading in UAV-Aided Mobile Edge Networks, Client Selection in Fault-Tolerant Federated Reinforcement Learning for IoT Networks, Energy-Efficient Federated Knowledge Distillation Learning in the Internet of Drones. This dissertation first investigated a Lyapunov optimization-based …
-
On-demand Crowdsourced Federated Learning over Edge Devices
… systems face significant challenges in scaling client participation and handling data heterogeneity, which impede the training of high-performing models. To address these limitations, this thesis argues that there’s a need for a dynamic learning platform where edge devices could volunteer to …
-
Artificial Intelligence in Computer Networks: Delay Estimation, Fault Detection, and Network Automation
… at service initiation as in the case of server-client selection or continuously done to monitor the quality of service as in the case of quality assurance applications. We intend to apply artificial intelligence to minimize the dependency on such explicit measurements and hence, optimize the …
-
Security and Energy-Efficiency in Federated Learning
… models when communicated to the participating clients extend the behavior which is undesirable. Additionally, FL suffers from increased energy consumption at the edge device level due to local training and data collection along with communication overheads. In scenarios where the edge devices …
-
Application of Fusion based Deep Learning Models to Improve Millimeter Wave Beamforming
… distributed architecture incorporates two biased client selection strategies: MaxLoss and heuristic Multi-Armed Bandit (MAB). This innovative approach streamlines beam selection, improving scalability, robustness and dynamic adaptability.
-
ADAPTIVE COMMUNICATION-EFFICIENT FEDERATED LEARNING ON REAL-WORLD DATA
… and user privacy issues. The key idea is that clients can collaboratively train machine learning models without sharing data. As federated learning achieves collaborative learning in a privacy-preserving manner, it attracts increasingly more attention from both industry and academia. However, …
-
Securing Federated Learning: A Comprehensive Defence Against Privacy Attacks
… overhead, and inadequate attack prevention. Most client selection methods cannot reliably separate malicious and straggler clients, with even cutting-edge approaches struggling with herding and cold-start issues. Furthermore, recent state-of-the-art techniques frequently fail to defend against …
-
Robustness and Reliability of Federated Learning
… with users' privacy in mind, by never collecting clients' data during the training process. FL's process starts with the server sending a model to clients, then the clients train that model using their local data and send the updated model back to the server (only the trained parameter values of …
-
Towards Self-Evolving Non-Terrestrial Networks (NTN) via Federated Learning
… that jointly optimizes resource allocation, client selection, and HAPS placement. An upper bound for the convergence rate is derived and analytically proven. Simulations show FLSTRA reduces end-to-end delay by an order of magnitude over a purely terrestrial baseline while maintaining model …
-
Emerging machine learning methods and their applications to life sciences
… using a real dataset characterized by non-IID client distributions and severe class imbalance. We propose and evaluate principled client-selection strategies and sampling schemes that improve representativeness, stabilize convergence, and enhance minority-class performance while substantially …
-
Evaluation Assessment of Metropolitan Ministries “Uplift U™” Program and Preliminary Analysis of Collected Data
… collection and organization, outcomes measures, client selection standards, and how the program is portrayed as opposed to how it is actually run. Preliminary analysis of the collected data suggests that there are no relationships between demographic information such as education, employability, …
-
Performance Enhancement Schemesand Effective Incentives for Federated Learning
… information leakage, there are not enough clients willing to participate in FL training process. Common practice for the uploaded local models is an evenly weighted aggregation, assuming that each node of the network contributes to advancing the global model equally, which is unfair with …
-
Implementing a hybrid federated learning framework with neural network optimisation for improved artificial intelligence model performance
… it proposes a flexible three-tier architecture (client–edge–cloud) that incorporates heuristics for intelligent client selection, communication cost reduction, and enhanced data privacy. Additionally, a strategy tailoring tool (FLATT) is developed, enabling designers to configure and adapt FL …
-
Federated, multi-agent, deep reinforcement learning
… model architectures, data partitioning and client selection, representation learning and federated distillation, incremental learning and knowledge retention, and training models with limited data. Each study contributed to the field by developing innovative algorithms, tested in simulated …
-
Towards Trustworthy Federated Learning: Security, Privacy, and Verifiability
… not hold in adversarial environments. Malicious clients may omit or falsify computation, inject poisoned updates, or free-ride on collective training with negligible detection risk. Existing defenses address security, privacy, and verifiability in isolation: privacy mechanisms obscure the signals …
Page 1 of 3