Concept Drift Detection in Federated Networked Systems
This addresses concept drift in federated learning for critical networked systems like Intelligent Transportation Systems, but it is incremental as it applies existing techniques to a specific domain.
The paper tackles concept drift in federated learning for networked systems by proposing a detection system using dimensionality reduction and clustering on federated updates, demonstrating its ability to detect drifted nodes in non-iid scenarios at various drift stages and exposure levels.
As next-generation networks materialize, increasing levels of intelligence are required. Federated Learning has been identified as a key enabling technology of intelligent and distributed networks; however, it is prone to concept drift as with any machine learning application. Concept drift directly affects the model's performance and can result in severe consequences considering the critical and emergency services provided by modern networks. To mitigate the adverse effects of drift, this paper proposes a concept drift detection system leveraging the federated learning updates provided at each iteration of the federated training process. Using dimensionality reduction and clustering techniques, a framework that isolates the system's drifted nodes is presented through experiments using an Intelligent Transportation System as a use case. The presented work demonstrates that the proposed framework is able to detect drifted nodes in a variety of non-iid scenarios at different stages of drift and different levels of system exposure.