MoCFL: Mobile Cluster Federated Learning Framework for Highly Dynamic Network
This addresses robustness challenges in federated learning for mobile networks, though it appears incremental as it builds on existing FL strategies with specific enhancements.
The paper tackles the problem of maintaining federated learning performance in highly dynamic mobile networks with frequent client churn and data drift, proposing MoCFL which uses an affinity matrix and historical feature integration to achieve superior robustness and accuracy on the UNSW-NB15 dataset.
Frequent fluctuations of client nodes in highly dynamic mobile clusters can lead to significant changes in feature space distribution and data drift, posing substantial challenges to the robustness of existing federated learning (FL) strategies. To address these issues, we proposed a mobile cluster federated learning framework (MoCFL). MoCFL enhances feature aggregation by introducing an affinity matrix that quantifies the similarity between local feature extractors from different clients, addressing dynamic data distribution changes caused by frequent client churn and topology changes. Additionally, MoCFL integrates historical and current feature information when training the global classifier, effectively mitigating the catastrophic forgetting problem frequently encountered in mobile scenarios. This synergistic combination ensures that MoCFL maintains high performance and stability in dynamically changing mobile environments. Experimental results on the UNSW-NB15 dataset show that MoCFL excels in dynamic environments, demonstrating superior robustness and accuracy while maintaining reasonable training costs.