An Adaptive Sampling Framework for Detecting Localized Concept Drift under Label Scarcity
By: Junghee Pyeon, Davide Cacciarelli, Kamran Paynabar
Potential Business Impact:
Finds hidden changes in data to improve predictions.
Concept drift and label scarcity are two critical challenges limiting the robustness of predictive models in dynamic industrial environments. Existing drift detection methods often assume global shifts and rely on dense supervision, making them ill-suited for regression tasks with local drifts and limited labels. This paper proposes an adaptive sampling framework that combines residual-based exploration and exploitation with EWMA monitoring to efficiently detect local concept drift under labeling budget constraints. Empirical results on synthetic benchmarks and a case study on electricity market demonstrate superior performance in label efficiency and drift detection accuracy.
Similar Papers
Flexible and Efficient Drift Detection without Labels
Machine Learning (Stat)
Finds when computer predictions stop being right.
Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network
Networking and Internet Architecture
Keeps smart networks working perfectly, even when things change.
Autonomous Concept Drift Threshold Determination
Machine Learning (CS)
Adapts computer learning to spot changes faster.