A Representation Learning Approach to Feature Drift Detection in Wireless Networks

Artificial Intelligence (AI) is foreseen to be a centerpiece in next generation wireless networks enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of Artificial Intelligence (AI) models and lead to undesired behaviors. To counter for undetected model degradation, we propose ALERT; a method that can detect feature distribution changes and trigger model re-training that works well on two wireless network use cases: wireless fingerprinting and link anomaly detection. ALERT includes three components: representation learning, statistical testing and utility assessment. We rely on Multi-layer Perceptron (MLP) for designing the representation learning component, on Kolmogorov-Smirnov (KS) and Population Stability Index (PSI) tests for designing the statistical testing and a new function for utility assessment. We show the superiority of the proposed method against ten standard drift detection methods available in the literature on two wireless network use cases.