DFedMQ: Decentralized Federated Learning Based on Dynamic Selection Collaboration and Topology Optimization

Bin Jiang, Junhao Wu, Guanghui Yue, Xuerong Cui, Jian Wang, Houbing Herbert Song

Abstract: Centralized federated learning is being widely researched and applied. However, centralized federated learning is prone to problems, such as single point of failure and privacy disclosure because it relies too much on the central server. Focusing on decentralized federated learning (DFL), this article innovatively constructs a DFL framework based on dynamic selection collaboration and topology optimization. First, we propose a dynamic client selection algorithm based on node training quality. Then, a global network topology for data communication is constructed by us based on the Watts–Strogatz (WS) model. Finally, we design a temporary topology algorithm to realize synchronization and model update in training. In the process of DFL, the global network topology based on WS model cooperates with the current network topology constructed by temporary topology algorithm. The two network topologies work together to realize a dynamic client selection algorithm based on node training quality. A large number of experiments verify that DFedMQ can accelerate the model convergence and improve the training effect under the premise of privacy protection.

External IDs:doi:10.1109/jiot.2025.3584095