Decentralized federated meta‐learning framework for few‐shot multitask learning. Issue 11 (7th July 2022)

• Record Type: Journal Article
• Authors: Li, Xiaoli; Li, Yuzheng; Wang, Jining; Chen, Chuan; Yang, Liu; Zheng, Zibin
• Is Part Of: International journal of intelligent systems. Volume 37:Issue 11(2022)
• Page Start: 8490
• Page End: 8522
• Publication Date: 2022-07-07
• Subjects: committee -- federated learning -- few shot -- meta‐learning -- multitask; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22951
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Federated learning is increasingly attractive, however as the number of training samples on a single device is too small and the training tasks of the devices are different, it faces the few‐shot multitask learning problem. Moreover, federated learning frameworks are usually vulnerable to malicious attacks of the central server and diverse clients. To address these problems, we propose a decentralized federated meta‐learning framework (DFMLF) for few‐shot multitask learning. In DFMLF, the devices take the rapid adaptation as objective and learn the meta‐knowledge shared by tasks to deal with the few‐shot multitask problem. In addition, DFMLF conducts cross‐validation and secure aggregation mechanism by a small number of committee nodes, which not only eliminates the central server to avoid the security risks brought by the malicious central server, but also avoids the attack of malicious devices. Moreover, to address the extra communication cost brought by the committee strategy, we propose a communication‐efficient method to make the training and aggregation carried out in parallel. We conduct extensive experiments based on real‐world data sets, and the experimental results demonstrate the effectiveness, robustness, and efficiency of our framework.