2026-04-20T04:00:34Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/4607452026-04-19T04:14:48Zcom_2072_1033col_2072_452951

Network-aware Federated learning Chen, Xi Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic Machine learning Electronic data processing--Distributed processing Federated learning Machine learning Large language models (LLMs) Communication efficiency Distributed machine learning Network Aprenentatge automàtic Processament distribuït de dades Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but it suffers from substantial communication overhead and sensitivity to heterogeneous client data and participation. In this thesis, we systematically investigate the federated learning process from both server-side orchestration and client-side training perspectives, with particular emphasis on how client participation patterns and data heterogeneity influence convergence behavior and communication efficiency. To address the high communication cost inherent in FL, we propose FedDB, a distance-based client selection strategy. FedDB evaluates the relative contribution of individual clients using model distance metrics computed at the server and selectively regulates client participation across training rounds. Importantly, the proposed method operates entirely at the server side and requires no modification to client-side training procedures or model architectures. We evaluate FedDB across multiple learning scenarios, including convolutional neural network (CNN) training and large language model (LLM) fine-tuning. Experimental results demonstrate that FedDB achieves significant communication savings-reducing client participation frequency by up to 60% compared to baseline federated learning strategies-while maintaining competitive predictive performance and stable convergence. Overall, this work highlights the effectiveness of dynamic, distance-based client selection for communication-efficient federated learning in distributed system. 2026-04-19T04:14:48Z 2026-04-19T04:14:48Z 2026-04-19T04:14:48Z 2026-01-28 Master thesis https://hdl.handle.net/2117/460745 Open Access Universitat Politècnica de Catalunya