S Bhatt, A Gupta, P Rai - Asian Conference on Machine …, 2024 - proceedings.mlr.press
Most existing federated learning methods are unable to estimate model/predictive uncertainty since the client models are trained using the standard loss function minimization …
Standard federated learning (FL) algorithms typically require multiple rounds of communication between the server and the clients, which has several drawbacks including …
The federated learning paradigm has motivated the development of methods for aggregating multiple client updates into a global server model, without sharing client data …
Federated learning methods enable model training across distributed data sources without data leaving their original locations and have gained increasing interest in various fields …
M Kim, T Hospedales - arXiv preprint arXiv:2305.04979, 2023 - arxiv.org
We propose a novel hierarchical Bayesian approach to Federated Learning (FL), where our model reasonably describes the generative process of clients' local data via hierarchical …
T d'Hondt, M Pechenizkiy, R Peharz - arXiv preprint arXiv:2406.02177, 2024 - arxiv.org
Optimization-based techniques for federated learning (FL) often come with prohibitive communication cost, as high dimensional model parameters need to be communicated …
H Chen, H Liu, Z Wu, X Fan, L Cao - arXiv preprint arXiv:2404.15657, 2024 - arxiv.org
While deep neural networks (DNNs) based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing …
Bayesian data fusion for distributed learning by Peng Wu Doctor of Philosophy in Electrical and Computer Engineering Northeastern University, April 2024 Prof. Pau Closas, Advisor …