Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion
Article
Shaik, Thanveer, Tao, Xiaohui, Li, Lin, Higgins, Niall, Gururajan, Raj, Zhou, Xujuan and Yong, Jianming. 2024. "Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion." Pattern Recognition Letters. 177. https://doi.org/10.1016/j.patrec.2023.12.004
| Article Title | Clustered FedStack: Intermediate Global Models with Bayesian Information Criterion |
|---|---|
| ERA Journal ID | 18106 |
| Article Category | Article |
| Authors | Shaik, Thanveer, Tao, Xiaohui, Li, Lin, Higgins, Niall, Gururajan, Raj, Zhou, Xujuan and Yong, Jianming |
| Journal Title | Pattern Recognition Letters |
| Journal Citation | 177 |
| Number of Pages | 7 |
| Year | 2024 |
| Publisher | Elsevier |
| Place of Publication | Netherlands |
| ISSN | 0167-8655 |
| 1872-7344 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.patrec.2023.12.004 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0167865523003513 |
| Abstract | Federated Learning (FL) is currently one of the most popular technologies in the field of Artificial Intelligence (AI) due to its collaborative learning and ability to preserve client privacy. However, it faces challenges such as non-identically and non-independently distributed (non-IID) data with imbalanced labels among local clients. To address these limitations, the research community has explored various approaches such as using local model parameters, federated generative adversarial learning, and federated representation learning. In our study, we propose a novel Clustered FedStack framework based on the previously published Stacked Federated Learning (FedStack) framework. Here, the local clients send their model predictions and output layer weights to a server, which then builds a robust global model. This global model clusters the local clients based on their output layer weights using a clustering mechanism. We adopt three clustering mechanisms, namely K-Means, Agglomerative, and Gaussian Mixture Models, into the framework and evaluate their performance. Bayesian Information Criterion (BIC) is used with the maximum likelihood function to determine the number of clusters. Our results show that Clustered FedStack models outperform baseline models with clustering mechanisms. To estimate the convergence of our proposed framework, we use Cyclical learning rates. |
| Keywords | Bayesian; Federated learning; FedStack; Clustering; Cyclical learning rates |
| Related Output | |
| Is part of | Revolutionizing healthcare with federated reinforcement learning: from machine learning to machine unlearning |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
| Public Notes | This article is part of a UniSQ Thesis by publication. See Related Output. |
| Byline Affiliations | School of Business |
| School of Mathematics, Physics and Computing | |
| Wuhan University of Technology, China | |
| Royal Brisbane and Women’s Hospital, Australia | |
| Queensland University of Technology |
Permalink -
https://research.usq.edu.au/item/z5vv4/clustered-fedstack-intermediate-global-models-with-bayesian-information-criterion
Download files
60
total views11
total downloads1
views this month1
downloads this month