Wu, Xiang and Zhang, Yong-Ting and Lai, Khin-Wee and Yang, Ming-Zhao and Yang, Ge-Lan and Wang, Huan-Huan (2025) A Novel Centralized Federated Deep Fuzzy Neural Network with Multi-objectives Neural Architecture Search for Epistatic Detection. IEEE Transactions on Fuzzy Systems, 33 (1). pp. 94-107. ISSN 1063-6706, DOI https://doi.org/10.1109/TFUZZ.2024.3369944.
Full text not available from this repository.Abstract
Epistasis detection (ED) was widely used for identifying potential risk disease variants in the human genome. A statistically meaningful ED typically requires a more extensive dataset to detect complex disease-associated single nucleotide polymorphisms, but a single institution generally possesses limited genome data. Thus, it is necessary to collect multi-institutional genome data to carry out research together. However, concerns regarding privacy and trustworthiness impede the sharing of massive genome data. Therefore, this article proposes a novel federated ED framework with the sequence perturbation privacy-preserving method to address the limitation of distributed data sharing (FedED-SegNAS). First, to address the lack of interpretability in deep learning models, integrate fuzzy logic into convolutional neural networks (CNNs), promoting the capabilities of CNN to represent the ambiguities of genomic data with high interpretability and reasonable accuracy. Second, consider using the neural architecture search method to optimize the federated neural architecture. Specifically, selecting the particle swarm optimization algorithm to automatically search the optimal neural architecture at different stages in federated learning (FL) based on adaptive multiobjectives decreases the communication cost and improves communication efficiency. Furthermore, to ensure the security of the parameter transfer process, design the sequence perturbation privacy-preserving method, grouping the upload and download parameters of FL and randomly perturbing the group number so that the attacker cannot obtain the corresponding result between the group number and parameters. Its rationality and security have been proven. The experiments conducted on a range of datasets demonstrate the superiority of the framework over state-of-the-art ED methods. FedED-SegNAS can reduce network complexity while protecting genome data security.
| Item Type: | Article |
|---|---|
| Funders: | National Natural Science Foundation of China (NSFC) (62003291), Xuzhou Science and Technology Project (KC22298), Basic Research (Natural Science) Project of Universities in Jiangsu Province (KY11022014), Key projects of the 14th five-year Plan of Education and Science in Jiangsu Province (B/2021/01/62) |
| Uncontrolled Keywords: | Computer architecture; Training; Neural networks; Optimization; Fuzzy systems; Fuzzy logic; Genomics; Deep neural fuzzy network; epistasis detection; federated learning; neural architecture search; particle swarm optimization |
| Subjects: | T Technology > TA Engineering (General). Civil engineering (General) |
| Divisions: | Faculty of Engineering |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 13 Mar 2025 02:18 |
| Last Modified: | 13 Mar 2025 02:18 |
| URI: | http://eprints.um.edu.my/id/eprint/47769 |
Actions (login required)
 |
View Item |
