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 40 for “"Non-IID data"”.
-
Weighted Ensemble Distillation in Federated Learning with Non-IID Data
… model predictions on an unlabeled auxiliary dataset into a global model. While standard FL algorithms are often based on averaging local parameter updates over multiple communication rounds, FD can be performed with only one communication round, giving favorable communication properties when …
-
Multi-Center Federated Learning to Cluster Clients with non-IID data
… across many clients without uploading local data to the server. Non-IID data across clients is a significant challenge for the FL system because its inherited distributed machine learning framework is designed for the scenario of IID data across clients. Clustered FL is a type of FL method to …
-
Federated learning model complexity vs robustness to non-IID data and selective federated learning
Federated learning trains a global model using data distributed across local nodes, and differs from centralized machine learning by moving the computation to the data in order to address the challenges of data ownership, privacy, computational power, and data storage. Previous federated learning …
-
Towards More Efficient Collaborative Distributed Data Analysis and Learning
… to the persistent generation of large amounts of data with rapid speed and broad geographical distribution. Obtaining knowledge and understanding via analysis and learning from such data have invaluable worth. Features of such data analytical tasks commonly include: data can be large scale and …
-
Trajectory Prediction for Automotive Applications using Federated Learning
… large quantities of continuously collected data, and must follow safety and privacy regulations. Federated learning (FL) enables the training of DL models to be done locally at each client (vehicle), sharing and aggregating the trained models while keeping the data local. This allows …
-
Statistical process control performance characterization under field conditions
… performance characteristics, considering both iid and non-iid data streams with and without step shifts in the data stream. The step shifts can be in location and/or in dispersion. The tool has three modules (1) simulation module, (2) performance module and (3) Output/report module and is …
-
Exploration in Personalized Federated Learning under Heterogeneous Multi-modal Environments
… research questions: (1) Personalization under Non-IID data: How can I design more effective personalization strategies to mitigate the adverse effects of non-IID data distributions? (2) Personalization for Missing Modality in Multimodal FL: How can I address the problem of missing modalities in …
-
Deep Learning Enhancement and Privacy-Preserving Deep Learning: A Data-Centric Approach
… important information from large amounts of data. While most of the work focuses on finding the best model parameters, improving machine learning performance from data perspective still needs more attention. In this work, we propose techniques to enhance the robustness of deep learning …
-
MODEL-CENTRIC COLLABORATIVE MACHINE LEARNING: SHARING, FUSION, MAINTENANCE AND APPLICATION
… training across devices without sharing raw data, promoting privacy-preserving machine learning. This dissertation focuses on model-centric collaborative learning, which exchanges models rather than gradients to enhance privacy and scalability—especially in one-shot FL scenarios. It proposes …
-
Collaborative Federated Learning for Robots in Heterogeneous Environments
… robotic agents. The study explores the impact of data heterogeneity on both the convergence of FedAvg and the fairness of learning, with regard to consistency of performance across agents. Experiments were conducted with simulated robots trained to perform a target collection task, where a subset …
-
Phoenix: Federated Learning for Generative Diffusion Model
… training generative models on large centralized datasets can pose challenges in terms of data privacy, security, and accessibility. Federated learning is an approach that uses decentralized techniques to collaboratively train a shared deep learning model while retaining the training data on …
-
Communication-efficient personalization in federated learning for edge devices
… of heterogeneity, limited resources, and diverse data modalities. It develops algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb …
-
Evaluating the Performance of Federated Learning A Case Study of Distributed Machine Learning with Erlang
… same distributed clients that generate training data. Contrary to centralised optimisation, clients in the setting of Federated Learning can be very large in number and are characterised by challenges of data and network heterogeneity. Examples of clients include smartphones and connected …
-
Graphical Models: Modeling, Optimization, and Hilbert Space Embedding
… assumed that, conditioned on the training data, the label sequences of different training examples are independent and identically distributed (iid). We extended the use of CRFs to a class of temporal learning algorithms, namely policy gradient reinforcement learning (RL). Now the labels …
-
P2P Based Personalized Federated Learning for Collaborative Model Sharing and Inferencing
… a single global model utilizing various local datasets. There are ongoing initiatives to improve the present state of federated learning. This method may not be suitable for clients with diverse requirements. For best outcomes, we need to explore distributed design, such as Peer-to-Peer (P2P), …
-
Network Traffic Classification Under Label Scarcity and Privacy Constraints Using Federated Self-Supervised and Confident Learning
… scarcity, pseudo-label noise, privacy concerns, non-independent and non-identically distributed (non-IID) data, and class imbalance in distributed environments. This thesis proposes two interconnected frameworks to address these issues. The centralized approach integrates traffic-adapted …
-
Privacy-preserving federated learning framework
… train a shared model without exposing raw data. However, FL often suffers from degraded performance due to three core challenges: non-IID data distributions, residual privacy risks, and limited data volume per node. This work explores the privacy–performance trade-offs arising from these …
-
Federated Learning and Incremental Learning: Private Non-IID Learning
In traditional centralized Deep Learning all the data is available at a certain place and time. Training a Machine Learning model in such a scenario is rather straightforward and also well-studied. However, there are many scenarios, where this is not the case: scenarios where the data is scattered …
-
Exploring Efficiency in Split Federated Learning under System Heterogeneity: A Study of System Synchronization and Resource Optimization
… experiments on VGG-16 using the Tiny-ImageNet dataset under non-IID data partitions demonstrate that CSFL significantly reduces training latency and energy consumption while maintaining accuracy comparable to conventional SFL. Overall, this work advances collaborative edge learning by …
-
Personalized Distributed Machine Learning With Graphs
… linkedthrough communication, resource, and data-similarity graphs, while the data they col- lect are often graphs themselves. This thesis shows that explicitly modeling both layers of structure unlocks accurate, efficient, and scalable personalized federated learning (PFL). At the network …
Page 1 of 2