no code implementations • 10 Mar 2024 • A. Jung
A key challenge in federated learning applications is the statistical heterogeneity of local datasets.
no code implementations • 8 Feb 2023 • A. Jung, S. Abdurakhmanova, O. Kuznetsova, Y. Sarcheshmehpour
Our method is an instance of empirical risk minimization, with the regularization term derived from the network structure of data.
no code implementations • 20 Jun 2022 • Y. Sarcheshmehpour, Y. Tian, L. Zhang, A. Jung
What sets our approach apart from spectral clustering is that we do not use the eigenvectors of a graph Laplacian to construct the feature vectors.
2 code implementations • 27 Oct 2020 • Y. Sarcheshmehpour, M. Leinonen, A. Jung
We obtain a distributed federated learning algorithm via a message passing implementation of this primal-dual method.
no code implementations • 3 Sep 2020 • L. Zhang, G. Karakasidis, A. Odnoblyudova, L. Dogruel, A. Jung
One user might have a university degree in machine learning or related fields, while another user might have never received formal training in high-school mathematics.
no code implementations • 22 Aug 2018 • A. Jung, N. Vesselinova
This approach lends quite naturally to highly scalable learning algorithms in the form of message passing over an empirical graph which represents the network structure of the data.